huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 20:04:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into safetensors_docs

Browse Source
This commit is contained in:
Merve Noyan 2023-09-07 15:47:55 +03:00 committed by GitHub
commit 0ef535e77e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
49 changed files with 2522 additions and 820 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Cargo.toml
View File

@ -8,7 +8,7 @@ members = [
] ]
[workspace.package] [workspace.package]
version = "1.0.1" version = "1.0.3"
edition = "2021" edition = "2021"
authors = ["Olivier Dehaene"] authors = ["Olivier Dehaene"]
homepage = "https://github.com/huggingface/text-generation-inference" homepage = "https://github.com/huggingface/text-generation-inference"

5
README.md
View File

@ -67,6 +67,7 @@ to power Hugging Chat, the Inference API and Inference Endpoint.
- [Falcon 40B](https://huggingface.co/tiiuae/falcon-40b) - [Falcon 40B](https://huggingface.co/tiiuae/falcon-40b)
- [MPT](https://huggingface.co/mosaicml/mpt-30b) - [MPT](https://huggingface.co/mosaicml/mpt-30b)
- [Llama V2](https://huggingface.co/meta-llama) - [Llama V2](https://huggingface.co/meta-llama)
- [Code Llama](https://huggingface.co/codellama)
Other architectures are supported on a best effort basis using: Other architectures are supported on a best effort basis using:
@ -86,7 +87,7 @@ The easiest way of getting started is using the official Docker container:
model=tiiuae/falcon-7b-instruct model=tiiuae/falcon-7b-instruct
volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.1 --model-id $model docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.3 --model-id $model
``` ```
**Note:** To use GPUs, you need to install the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html). We also recommend using NVIDIA drivers with CUDA version 11.8 or higher. For running the Docker container on a machine with no GPUs or CUDA support, it is enough to remove the `--gpus all` flag and add `--disable-custom-kernels`, please note CPU is not the intended platform for this project, so performance might be subpar. **Note:** To use GPUs, you need to install the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html). We also recommend using NVIDIA drivers with CUDA version 11.8 or higher. For running the Docker container on a machine with no GPUs or CUDA support, it is enough to remove the `--gpus all` flag and add `--disable-custom-kernels`, please note CPU is not the intended platform for this project, so performance might be subpar.
@ -153,7 +154,7 @@ model=meta-llama/Llama-2-7b-chat-hf
volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
token=<your cli READ token> token=<your cli READ token>
docker run --gpus all --shm-size 1g -e HUGGING_FACE_HUB_TOKEN=$token -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.1 --model-id $model docker run --gpus all --shm-size 1g -e HUGGING_FACE_HUB_TOKEN=$token -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.3 --model-id $model
``` ```
### A note on Shared Memory (shm) ### A note on Shared Memory (shm)

8
benchmark/src/generation.rs
View File

@ -37,6 +37,7 @@ pub(crate) async fn generation_task(
batch_size: Vec<u32>, batch_size: Vec<u32>,
sequence_length: u32, sequence_length: u32,
decode_length: u32, decode_length: u32,
top_n_tokens: Option<u32>,
n_runs: usize, n_runs: usize,
warmups: usize, warmups: usize,
parameters: NextTokenChooserParameters, parameters: NextTokenChooserParameters,
@ -48,7 +49,7 @@ pub(crate) async fn generation_task(
// End task if a message is received on shutdown_receiver // End task if a message is received on shutdown_receiver
// _shutdown_guard_sender will be dropped once the task is finished // _shutdown_guard_sender will be dropped once the task is finished
tokio::select! { tokio::select! {
res = generate_runs(tokenizer, batch_size, sequence_length, decode_length, n_runs, warmups, parameters, client, run_sender.clone()) => { res = generate_runs(tokenizer, batch_size, sequence_length, decode_length, top_n_tokens, n_runs, warmups, parameters, client, run_sender.clone()) => {
if let Err(err) = res { if let Err(err) = res {
run_sender.send(Err(err)).await.unwrap_or(()); run_sender.send(Err(err)).await.unwrap_or(());
} }
@ -64,6 +65,7 @@ async fn generate_runs(
batch_size: Vec<u32>, batch_size: Vec<u32>,
sequence_length: u32, sequence_length: u32,
decode_length: u32, decode_length: u32,
top_n_tokens: Option<u32>,
n_runs: usize, n_runs: usize,
warmups: usize, warmups: usize,
parameters: NextTokenChooserParameters, parameters: NextTokenChooserParameters,
@ -82,6 +84,7 @@ async fn generate_runs(
b, b,
decode_length, decode_length,
parameters.clone(), parameters.clone(),
top_n_tokens,
&mut client, &mut client,
) )
.await?; .await?;
@ -97,6 +100,7 @@ async fn generate_runs(
b, b,
decode_length, decode_length,
parameters.clone(), parameters.clone(),
top_n_tokens,
&mut client, &mut client,
) )
.await?; .await?;
@ -130,6 +134,7 @@ async fn prefill(
batch_size: u32, batch_size: u32,
decode_length: u32, decode_length: u32,
parameters: NextTokenChooserParameters, parameters: NextTokenChooserParameters,
top_n_tokens: Option<u32>,
client: &mut ShardedClient, client: &mut ShardedClient,
) -> Result<(Prefill, CachedBatch), ClientError> { ) -> Result<(Prefill, CachedBatch), ClientError> {
// Create requests // Create requests
@ -145,6 +150,7 @@ async fn prefill(
stop_sequences: vec![], stop_sequences: vec![],
ignore_eos_token: true, // Will not stop even if a eos token is generated ignore_eos_token: true, // Will not stop even if a eos token is generated
}), }),
top_n_tokens: top_n_tokens.unwrap_or(0),
}) })
.collect(); .collect();

3
benchmark/src/lib.rs
View File

@ -22,6 +22,7 @@ pub async fn run(
batch_size: Vec<u32>, batch_size: Vec<u32>,
sequence_length: u32, sequence_length: u32,
decode_length: u32, decode_length: u32,
top_n_tokens: Option<u32>,
n_runs: usize, n_runs: usize,
warmups: usize, warmups: usize,
temperature: Option<f32>, temperature: Option<f32>,
@ -70,6 +71,7 @@ pub async fn run(
batch_size.clone(), batch_size.clone(),
sequence_length, sequence_length,
decode_length, decode_length,
top_n_tokens,
n_runs, n_runs,
warmups, warmups,
parameters, parameters,
@ -130,6 +132,7 @@ pub async fn run(
tokenizer_name, tokenizer_name,
sequence_length, sequence_length,
decode_length, decode_length,
top_n_tokens,
n_runs, n_runs,
warmups, warmups,
temperature, temperature,

7
benchmark/src/main.rs
View File

@ -93,6 +93,11 @@ struct Args {
/// decoding strategies, for full doc refer to the `text-generation-server` /// decoding strategies, for full doc refer to the `text-generation-server`
#[clap(long, env)] #[clap(long, env)]
do_sample: bool, do_sample: bool,
/// Generation parameter in case you want to specifically test/debug particular
/// decoding strategies, for full doc refer to the `text-generation-server`
#[clap(long, env)]
top_n_tokens: Option<u32>,
} }
fn main() -> Result<(), Box<dyn std::error::Error>> { fn main() -> Result<(), Box<dyn std::error::Error>> {
@ -117,6 +122,7 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
watermark, watermark,
do_sample, do_sample,
master_shard_uds_path, master_shard_uds_path,
top_n_tokens,
} = args; } = args;
let batch_size = batch_size.unwrap_or(vec![1, 2, 4, 8, 16, 32]); let batch_size = batch_size.unwrap_or(vec![1, 2, 4, 8, 16, 32]);
@ -173,6 +179,7 @@ fn main() -> Result<(), Box<dyn std::error::Error>> {
batch_size, batch_size,
sequence_length, sequence_length,
decode_length, decode_length,
top_n_tokens,
runs, runs,
warmups, warmups,
temperature, temperature,

2
benchmark/src/table.rs
View File

@ -7,6 +7,7 @@ pub(crate) fn parameters_table(
tokenizer_name: String, tokenizer_name: String,
sequence_length: u32, sequence_length: u32,
decode_length: u32, decode_length: u32,
top_n_tokens: Option<u32>,
n_runs: usize, n_runs: usize,
warmups: usize, warmups: usize,
temperature: Option<f32>, temperature: Option<f32>,
@ -24,6 +25,7 @@ pub(crate) fn parameters_table(
builder.push_record(["Model", &tokenizer_name]); builder.push_record(["Model", &tokenizer_name]);
builder.push_record(["Sequence Length", &sequence_length.to_string()]); builder.push_record(["Sequence Length", &sequence_length.to_string()]);
builder.push_record(["Decode Length", &decode_length.to_string()]); builder.push_record(["Decode Length", &decode_length.to_string()]);
builder.push_record(["Top N Tokens", &format!("{top_n_tokens:?}")]);
builder.push_record(["N Runs", &n_runs.to_string()]); builder.push_record(["N Runs", &n_runs.to_string()]);
builder.push_record(["Warmups", &warmups.to_string()]); builder.push_record(["Warmups", &warmups.to_string()]);
builder.push_record(["Temperature", &format!("{temperature:?}")]); builder.push_record(["Temperature", &format!("{temperature:?}")]);

2
clients/python/pyproject.toml
View File

@ -12,7 +12,7 @@ repository = "https://github.com/huggingface/text-generation-inference"
[tool.poetry.dependencies] [tool.poetry.dependencies]
python = "^3.7" python = "^3.7"
pydantic = "^1.10" pydantic = "> 1.10, < 3"
aiohttp = "^3.8" aiohttp = "^3.8"
huggingface-hub = ">= 0.12, < 1.0" huggingface-hub = ">= 0.12, < 1.0"

2
clients/python/text_generation/__init__.py
View File

@ -12,7 +12,7 @@
# See the License for the specific language governing permissions and # See the License for the specific language governing permissions and
# limitations under the License. # limitations under the License.
__version__ = "0.3.0" __version__ = "0.6.0"
from text_generation.client import Client, AsyncClient from text_generation.client import Client, AsyncClient
from text_generation.inference_api import InferenceAPIClient, InferenceAPIAsyncClient from text_generation.inference_api import InferenceAPIClient, InferenceAPIAsyncClient

16
clients/python/text_generation/client.py
View File

@ -75,6 +75,7 @@ class Client:
typical_p: Optional[float] = None, typical_p: Optional[float] = None,
watermark: bool = False, watermark: bool = False,
decoder_input_details: bool = False, decoder_input_details: bool = False,
top_n_tokens: Optional[int] = None,
) -> Response: ) -> Response:
""" """
Given a prompt, generate the following text Given a prompt, generate the following text
@ -113,6 +114,8 @@ class Client:
Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226) Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226)
decoder_input_details (`bool`): decoder_input_details (`bool`):
Return the decoder input token logprobs and ids Return the decoder input token logprobs and ids
top_n_tokens (`int`):
Return the `n` most likely tokens at each step
Returns: Returns:
Response: generated response Response: generated response
@ -134,6 +137,7 @@ class Client:
typical_p=typical_p, typical_p=typical_p,
watermark=watermark, watermark=watermark,
decoder_input_details=decoder_input_details, decoder_input_details=decoder_input_details,
top_n_tokens=top_n_tokens
) )
request = Request(inputs=prompt, stream=False, parameters=parameters) request = Request(inputs=prompt, stream=False, parameters=parameters)
@ -164,6 +168,7 @@ class Client:
truncate: Optional[int] = None, truncate: Optional[int] = None,
typical_p: Optional[float] = None, typical_p: Optional[float] = None,
watermark: bool = False, watermark: bool = False,
top_n_tokens: Optional[int] = None,
) -> Iterator[StreamResponse]: ) -> Iterator[StreamResponse]:
""" """
Given a prompt, generate the following stream of tokens Given a prompt, generate the following stream of tokens
@ -198,6 +203,8 @@ class Client:
See [Typical Decoding for Natural Language Generation](https://arxiv.org/abs/2202.00666) for more information See [Typical Decoding for Natural Language Generation](https://arxiv.org/abs/2202.00666) for more information
watermark (`bool`): watermark (`bool`):
Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226) Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226)
top_n_tokens (`int`):
Return the `n` most likely tokens at each step
Returns: Returns:
Iterator[StreamResponse]: stream of generated tokens Iterator[StreamResponse]: stream of generated tokens
@ -219,6 +226,7 @@ class Client:
truncate=truncate, truncate=truncate,
typical_p=typical_p, typical_p=typical_p,
watermark=watermark, watermark=watermark,
top_n_tokens=top_n_tokens,
) )
request = Request(inputs=prompt, stream=True, parameters=parameters) request = Request(inputs=prompt, stream=True, parameters=parameters)
@ -317,6 +325,7 @@ class AsyncClient:
typical_p: Optional[float] = None, typical_p: Optional[float] = None,
watermark: bool = False, watermark: bool = False,
decoder_input_details: bool = False, decoder_input_details: bool = False,
top_n_tokens: Optional[int] = None,
) -> Response: ) -> Response:
""" """
Given a prompt, generate the following text asynchronously Given a prompt, generate the following text asynchronously
@ -355,6 +364,8 @@ class AsyncClient:
Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226) Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226)
decoder_input_details (`bool`): decoder_input_details (`bool`):
Return the decoder input token logprobs and ids Return the decoder input token logprobs and ids
top_n_tokens (`int`):
Return the `n` most likely tokens at each step
Returns: Returns:
Response: generated response Response: generated response
@ -376,6 +387,7 @@ class AsyncClient:
truncate=truncate, truncate=truncate,
typical_p=typical_p, typical_p=typical_p,
watermark=watermark, watermark=watermark,
top_n_tokens=top_n_tokens,
) )
request = Request(inputs=prompt, stream=False, parameters=parameters) request = Request(inputs=prompt, stream=False, parameters=parameters)
@ -404,6 +416,7 @@ class AsyncClient:
truncate: Optional[int] = None, truncate: Optional[int] = None,
typical_p: Optional[float] = None, typical_p: Optional[float] = None,
watermark: bool = False, watermark: bool = False,
top_n_tokens: Optional[int] = None,
) -> AsyncIterator[StreamResponse]: ) -> AsyncIterator[StreamResponse]:
""" """
Given a prompt, generate the following stream of tokens asynchronously Given a prompt, generate the following stream of tokens asynchronously
@ -438,6 +451,8 @@ class AsyncClient:
See [Typical Decoding for Natural Language Generation](https://arxiv.org/abs/2202.00666) for more information See [Typical Decoding for Natural Language Generation](https://arxiv.org/abs/2202.00666) for more information
watermark (`bool`): watermark (`bool`):
Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226) Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226)
top_n_tokens (`int`):
Return the `n` most likely tokens at each step
Returns: Returns:
AsyncIterator[StreamResponse]: stream of generated tokens AsyncIterator[StreamResponse]: stream of generated tokens
@ -459,6 +474,7 @@ class AsyncClient:
truncate=truncate, truncate=truncate,
typical_p=typical_p, typical_p=typical_p,
watermark=watermark, watermark=watermark,
top_n_tokens=top_n_tokens,
) )
request = Request(inputs=prompt, stream=True, parameters=parameters) request = Request(inputs=prompt, stream=True, parameters=parameters)

48
clients/python/text_generation/types.py
View File

@ -18,27 +18,29 @@ class Parameters(BaseModel):
# Stop generating tokens if a member of `stop_sequences` is generated # Stop generating tokens if a member of `stop_sequences` is generated
stop: List[str] = [] stop: List[str] = []
# Random sampling seed # Random sampling seed
seed: Optional[int] seed: Optional[int] = None
# The value used to module the logits distribution. # The value used to module the logits distribution.
temperature: Optional[float] temperature: Optional[float] = None
# The number of highest probability vocabulary tokens to keep for top-k-filtering. # The number of highest probability vocabulary tokens to keep for top-k-filtering.
top_k: Optional[int] top_k: Optional[int] = None
# If set to < 1, only the smallest set of most probable tokens with probabilities that add up to `top_p` or # If set to < 1, only the smallest set of most probable tokens with probabilities that add up to `top_p` or
# higher are kept for generation. # higher are kept for generation.
top_p: Optional[float] top_p: Optional[float] = None
# truncate inputs tokens to the given size # truncate inputs tokens to the given size
truncate: Optional[int] truncate: Optional[int] = None
# Typical Decoding mass # Typical Decoding mass
# See [Typical Decoding for Natural Language Generation](https://arxiv.org/abs/2202.00666) for more information # See [Typical Decoding for Natural Language Generation](https://arxiv.org/abs/2202.00666) for more information
typical_p: Optional[float] typical_p: Optional[float] = None
# Generate best_of sequences and return the one if the highest token logprobs # Generate best_of sequences and return the one if the highest token logprobs
best_of: Optional[int] best_of: Optional[int] = None
# Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226) # Watermarking with [A Watermark for Large Language Models](https://arxiv.org/abs/2301.10226)
watermark: bool = False watermark: bool = False
# Get generation details # Get generation details
details: bool = False details: bool = False
# Get decoder input token logprobs and ids # Get decoder input token logprobs and ids
decoder_input_details: bool = False decoder_input_details: bool = False
# Return the N most likely tokens at each step
top_n_tokens: Optional[int]
@validator("best_of") @validator("best_of")
def valid_best_of(cls, field_value, values): def valid_best_of(cls, field_value, values):
@ -101,12 +103,18 @@ class Parameters(BaseModel):
raise ValidationError("`typical_p` must be > 0.0 and < 1.0") raise ValidationError("`typical_p` must be > 0.0 and < 1.0")
return v return v
@validator("top_n_tokens")
def valid_top_n_tokens(cls, v):
if v is not None and v <= 0:
raise ValidationError("`top_n_tokens` must be strictly positive")
return v
class Request(BaseModel): class Request(BaseModel):
# Prompt # Prompt
inputs: str inputs: str
# Generation parameters # Generation parameters
parameters: Optional[Parameters] parameters: Optional[Parameters] = None
# Whether to stream output tokens # Whether to stream output tokens
stream: bool = False stream: bool = False
@ -125,9 +133,7 @@ class Request(BaseModel):
and parameters.best_of > 1 and parameters.best_of > 1
and field_value and field_value
): ):
raise ValidationError( raise ValidationError("`best_of` != 1 is not supported when `stream` == True")
"`best_of` != 1 is not supported when `stream` == True"
)
return field_value return field_value
@ -139,7 +145,7 @@ class InputToken(BaseModel):
text: str text: str
# Logprob # Logprob
# Optional since the logprob of the first token cannot be computed # Optional since the logprob of the first token cannot be computed
logprob: Optional[float] logprob: Optional[float] = None
# Generated tokens # Generated tokens
@ -174,11 +180,13 @@ class BestOfSequence(BaseModel):
# Number of generated tokens # Number of generated tokens
generated_tokens: int generated_tokens: int
# Sampling seed if sampling was activated # Sampling seed if sampling was activated
seed: Optional[int] seed: Optional[int] = None
# Decoder input tokens, empty if decoder_input_details is False # Decoder input tokens, empty if decoder_input_details is False
prefill: List[InputToken] prefill: List[InputToken]
# Generated tokens # Generated tokens
tokens: List[Token] tokens: List[Token]
# Most likely tokens
top_tokens: Optional[List[List[Token]]]
# `generate` details # `generate` details
@ -188,13 +196,15 @@ class Details(BaseModel):
# Number of generated tokens # Number of generated tokens
generated_tokens: int generated_tokens: int
# Sampling seed if sampling was activated # Sampling seed if sampling was activated
seed: Optional[int] seed: Optional[int] = None
# Decoder input tokens, empty if decoder_input_details is False # Decoder input tokens, empty if decoder_input_details is False
prefill: List[InputToken] prefill: List[InputToken]
# Generated tokens # Generated tokens
tokens: List[Token] tokens: List[Token]
# Most likely tokens
top_tokens: Optional[List[List[Token]]]
# Additional sequences when using the `best_of` parameter # Additional sequences when using the `best_of` parameter
best_of_sequences: Optional[List[BestOfSequence]] best_of_sequences: Optional[List[BestOfSequence]] = None
# `generate` return value # `generate` return value
@ -212,19 +222,21 @@ class StreamDetails(BaseModel):
# Number of generated tokens # Number of generated tokens
generated_tokens: int generated_tokens: int
# Sampling seed if sampling was activated # Sampling seed if sampling was activated
seed: Optional[int] seed: Optional[int] = None
# `generate_stream` return value # `generate_stream` return value
class StreamResponse(BaseModel): class StreamResponse(BaseModel):
# Generated token # Generated token
token: Token token: Token
# Most likely tokens
top_tokens: Optional[List[Token]]
# Complete generated text # Complete generated text
# Only available when the generation is finished # Only available when the generation is finished
generated_text: Optional[str] generated_text: Optional[str] = None
# Generation details # Generation details
# Only available when the generation is finished # Only available when the generation is finished
details: Optional[StreamDetails] details: Optional[StreamDetails] = None
# Inference API currently deployed model # Inference API currently deployed model

2
docs/openapi.json
View File

@ -10,7 +10,7 @@
"name": "Apache 2.0", "name": "Apache 2.0",
"url": "https://www.apache.org/licenses/LICENSE-2.0" "url": "https://www.apache.org/licenses/LICENSE-2.0"
}, },
"version": "1.0.1" "version": "1.0.3"
}, },
"paths": { "paths": {
"/": { "/": {

2
docs/source/_toctree.yml
View File

@ -23,4 +23,6 @@
title: Streaming title: Streaming
- local: conceptual/safetensors - local: conceptual/safetensors
title: Safetensors title: Safetensors
- local: conceptual/flash_attention
title: Flash Attention
title: Conceptual Guides title: Conceptual Guides

75
docs/source/basic_tutorials/consuming_tgi.md
View File

@ -75,6 +75,81 @@ To serve both ChatUI and TGI in same environment, simply add your own endpoints
![ChatUI](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/chatui_screen.png) ![ChatUI](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/chatui_screen.png)
## Gradio
Gradio is a Python library that helps you build web applications for your machine learning models with a few lines of code. It has a `ChatInterface` wrapper that helps create neat UIs for chatbots. Let's take a look at how to create a chatbot with streaming mode using TGI and Gradio. Let's install Gradio and Hub Python library first.
```bash
pip install huggingface-hub gradio
```
Assume you are serving your model on port 8080, we will query through [InferenceClient](consuming_tgi#inference-client).
```python
import gradio as gr
from huggingface_hub import InferenceClient
client = InferenceClient(model="http://127.0.0.1:8080")
def inference(message, history):
partial_message = ""
for token in client.text_generation(message, max_new_tokens=20, stream=True):
partial_message += token
yield partial_message
gr.ChatInterface(
inference,
chatbot=gr.Chatbot(height=300),
textbox=gr.Textbox(placeholder="Chat with me!", container=False, scale=7),
description="This is the demo for Gradio UI consuming TGI endpoint with LLaMA 7B-Chat model.",
title="Gradio 🤝 TGI",
examples=["Are tomatoes vegetables?"],
retry_btn="Retry",
undo_btn="Undo",
clear_btn="Clear",
).queue().launch()
```
The UI looks like this 👇
<div class="flex justify-center">
<img
class="block dark:hidden"
src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/tgi/gradio-tgi.png"
/>
<img
class="hidden dark:block"
src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/tgi/gradio-tgi-dark.png"
/>
</div>
You can try the demo directly here 👇
<div class="block dark:hidden">
<iframe
src="https://merve-gradio-tgi-2.hf.space?__theme=light"
width="850"
height="750"
></iframe>
</div>
<div class="hidden dark:block">
<iframe
src="https://merve-gradio-tgi-2.hf.space?__theme=dark"
width="850"
height="750"
></iframe>
</div>
You can disable streaming mode using `return` instead of `yield` in your inference function, like below.
```python
def inference(message, history):
return client.text_generation(message, max_new_tokens=20)
```
You can read more about how to customize a `ChatInterface` [here](https://www.gradio.app/guides/creating-a-chatbot-fast).
## API documentation ## API documentation
You can consult the OpenAPI documentation of the `text-generation-inference` REST API using the `/docs` route. The Swagger UI is also available [here](https://huggingface.github.io/text-generation-inference). You can consult the OpenAPI documentation of the `text-generation-inference` REST API using the `/docs` route. The Swagger UI is also available [here](https://huggingface.github.io/text-generation-inference).

12
docs/source/conceptual/flash_attention.md Normal file
View File

@ -0,0 +1,12 @@
# Flash Attention
Scaling the transformer architecture is heavily bottlenecked by the self-attention mechanism, which has quadratic time and memory complexity. Recent developments in accelerator hardware mainly focus on enhancing compute capacities and not memory and transferring data between hardware. This results in attention operation having a memory bottleneck. **Flash Attention** is an attention algorithm used to reduce this problem and scale transformer-based models more efficiently, enabling faster training and inference.
Standard attention mechanism uses High Bandwidth Memory (HBM) to store, read and write keys, queries and values. HBM is large in memory, but slow in processing, meanwhile SRAM is smaller in memory, but faster in operations. In the standard attention implementation, the cost of loading and writing keys, queries, and values from HBM is high. It loads keys, queries, and values from HBM to GPU on-chip SRAM, performs a single step of the attention mechanism, writes it back to HBM, and repeats this for every single attention step. Instead, Flash Attention loads keys, queries, and values once, fuses the operations of the attention mechanism, and writes them back.
![Flash Attention](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/tgi/flash-attn.png)
It is implemented for supported models. You can check out the complete list of models that support Flash Attention [here](https://github.com/huggingface/text-generation-inference/tree/main/server/text_generation_server/models), for models with flash prefix.
You can learn more about Flash Attention by reading the paper in this [link](https://arxiv.org/abs/2205.14135).

8
docs/source/conceptual/streaming.md
View File

@ -121,9 +121,9 @@ If you're using the free Inference API, you can use `HfInference`. If you're usi
We can create a `HfInferenceEndpoint` providing our endpoint URL and credential. We can create a `HfInferenceEndpoint` providing our endpoint URL and credential.
```js ```js
import { HfInference } from '@huggingface/inference' import { HfInferenceEndpoint } from '@huggingface/inference'
const hf = new HfInference('https://YOUR_ENDPOINT.endpoints.huggingface.cloud', 'hf_YOUR_TOKEN') const hf = new HfInferenceEndpoint('https://YOUR_ENDPOINT.endpoints.huggingface.cloud', 'hf_YOUR_TOKEN')
// prompt // prompt
const prompt = 'What can you do in Nuremberg, Germany? Give me 3 Tips' const prompt = 'What can you do in Nuremberg, Germany? Give me 3 Tips'
@ -143,6 +143,4 @@ SSEs are different than:
* Polling: where the client keeps calling the server to get data. This means that the server might return empty responses and cause overhead. * Polling: where the client keeps calling the server to get data. This means that the server might return empty responses and cause overhead.
* Webhooks: where there is a bi-directional connection. The server can send information to the client, but the client can also send data to the server after the first request. Webhooks are more complex to operate as they don’t only use HTTP. * Webhooks: where there is a bi-directional connection. The server can send information to the client, but the client can also send data to the server after the first request. Webhooks are more complex to operate as they don’t only use HTTP.
One of the limitations of Server-Sent Events is that they limit how many concurrent requests can handle by the server. Instead of timing out when there are too many SSE connections, TGI returns a HTTP Error with an `overloaded` error type (`huggingface_hub` returns `OverloadedError`). This allows the client to manage the overloaded server (e.g. it could display a busy error to the user or it could retry with a new request). To configure the maximum number of concurrent requests, you can specify `--max_concurrent_requests`, allowing to handle backpressure. If there are too many requests at the same time, TGI returns an HTTP Error with an `overloaded` error type (`huggingface_hub` returns `OverloadedError`). This allows the client to manage the overloaded server (e.g., it could display a busy error to the user or retry with a new request). To configure the maximum number of concurrent requests, you can specify `--max_concurrent_requests`, allowing clients to handle backpressure.
One of the limitations of Server-Sent Events is that they limit how many concurrent requests can handle by the server. Instead of timing out when there are too many SSE connections, TGI returns an HTTP Error with an `overloaded` error type (`huggingface_hub` returns `OverloadedError`). This allows the client to manage the overloaded server (e.g., it could display a busy error to the user or retry with a new request). To configure the maximum number of concurrent requests, you can specify `--max_concurrent_requests`, allowing clients to handle backpressure.

4
docs/source/quicktour.md
View File

@ -8,7 +8,7 @@ Let's say you want to deploy [Falcon-7B Instruct](https://huggingface.co/tiiuae/
model=tiiuae/falcon-7b-instruct model=tiiuae/falcon-7b-instruct
volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.1 --model-id $model docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.3 --model-id $model
``` ```
<Tip warning={true}> <Tip warning={true}>
@ -85,7 +85,7 @@ curl 127.0.0.1:8080/generate \
To see all possible deploy flags and options, you can use the `--help` flag. It's possible to configure the number of shards, quantization, generation parameters, and more. To see all possible deploy flags and options, you can use the `--help` flag. It's possible to configure the number of shards, quantization, generation parameters, and more.
```bash ```bash
docker run ghcr.io/huggingface/text-generation-inference:1.0.1 --help docker run ghcr.io/huggingface/text-generation-inference:1.0.3 --help
``` ```
</Tip> </Tip>

69
integration-tests/models/__snapshots__/test_idefics/test_idefics.json
View File

@ -11,52 +11,52 @@
}, },
{ {
"id": 4911, "id": 4911,
"logprob": -5.3632812, "logprob": -5.7773438,
"text": "User" "text": "User"
}, },
{ {
"id": 29901, "id": 29901,
"logprob": -0.00762558, "logprob": -0.0069999695,
"text": ":" "text": ":"
}, },
{ {
"id": 32000, "id": 32000,
"logprob": -0.7739258, "logprob": -0.8125,
"text": "<fake_token_around_image>" "text": "<fake_token_around_image>"
}, },
{ {
"id": 32001, "id": 32001,
"logprob": -9.775162e-05, "logprob": -6.651878e-05,
"text": "<image>" "text": "<image>"
}, },
{ {
"id": 32000, "id": 32000,
"logprob": -1.1920929e-07, "logprob": -3.5762787e-07,
"text": "<fake_token_around_image>" "text": "<fake_token_around_image>"
}, },
{ {
"id": 1815, "id": 1815,
"logprob": -4.4140625, "logprob": -4.2265625,
"text": "Can" "text": "Can"
}, },
{ {
"id": 366, "id": 366,
"logprob": -0.01436615, "logprob": -0.013977051,
"text": "you" "text": "you"
}, },
{ {
"id": 2649, "id": 2649,
"logprob": -4.9414062, "logprob": -4.4375,
"text": "tell" "text": "tell"
}, },
{ {
"id": 592, "id": 592,
"logprob": -0.3005371, "logprob": -0.29077148,
"text": "me" "text": "me"
}, },
{ {
"id": 263, "id": 263,
"logprob": -3.5703125, "logprob": -4.2109375,
"text": "a" "text": "a"
}, },
{ {
@ -66,37 +66,37 @@
}, },
{ {
"id": 3273, "id": 3273,
"logprob": -1.9111328, "logprob": -1.8671875,
"text": "short" "text": "short"
}, },
{ {
"id": 5828, "id": 5828,
"logprob": -0.28881836, "logprob": -0.26586914,
"text": "story" "text": "story"
}, },
{ {
"id": 2729, "id": 2729,
"logprob": -3.4179688, "logprob": -3.7460938,
"text": "based" "text": "based"
}, },
{ {
"id": 373, "id": 373,
"logprob": -0.00056886673, "logprob": -0.0005350113,
"text": "on" "text": "on"
}, },
{ {
"id": 278, "id": 278,
"logprob": -0.14123535, "logprob": -0.13867188,
"text": "the" "text": "the"
}, },
{ {
"id": 1967, "id": 1967,
"logprob": -0.053985596, "logprob": -0.06842041,
"text": "image" "text": "image"
}, },
{ {
"id": 29973, "id": 29973,
"logprob": -0.15771484, "logprob": -0.15319824,
"text": "?" "text": "?"
} }
], ],
@ -104,25 +104,25 @@
"tokens": [ "tokens": [
{ {
"id": 32002, "id": 32002,
"logprob": -0.004295349, "logprob": -0.0019445419,
"special": true, "special": true,
"text": "<end_of_utterance>" "text": "<end_of_utterance>"
}, },
{ {
"id": 29871, "id": 29871,
"logprob": -7.43866e-05, "logprob": -8.404255e-05,
"special": false, "special": false,
"text": " " "text": " "
}, },
{ {
"id": 13, "id": 13,
"logprob": -2.3126602e-05, "logprob": -1.7881393e-05,
"special": false, "special": false,
"text": "\n" "text": "\n"
}, },
{ {
"id": 7900, "id": 7900,
"logprob": -3.9339066e-06, "logprob": -3.0994415e-06,
"special": false, "special": false,
"text": "Ass" "text": "Ass"
}, },
@ -134,35 +134,36 @@
}, },
{ {
"id": 29901, "id": 29901,
"logprob": -2.6226044e-06, "logprob": -3.2186508e-06,
"special": false, "special": false,
"text": ":" "text": ":"
}, },
{ {
"id": 319, "id": 319,
"logprob": -0.87841797, "logprob": -0.9057617,
"special": false, "special": false,
"text": " A" "text": " A"
}, },
{ {
"id": 521, "id": 696,
"logprob": -1.3837891, "logprob": -1.2314453,
"special": false, "special": false,
"text": " ch" "text": " ro"
}, },
{ {
"id": 21475, "id": 15664,
"logprob": -0.00051641464, "logprob": -0.00024914742,
"special": false, "special": false,
"text": "icken" "text": "oster"
}, },
{ {
"id": 338, "id": 15028,
"logprob": -1.1435547, "logprob": -1.1621094,
"special": false, "special": false,
"text": " is" "text": " stands"
} }
] ],
"top_tokens": null
}, },
"generated_text": "\nAssistant: A chicken is" "generated_text": "\nAssistant: A rooster stands"
} }

1080
integration-tests/models/__snapshots__/test_idefics/test_idefics_load.json
View File

File diff suppressed because it is too large Load Diff

982
integration-tests/poetry.lock generated Normal file
View File

@ -0,0 +1,982 @@
# This file is automatically @generated by Poetry 1.5.1 and should not be changed by hand.
[[package]]
name = "aiohttp"
version = "3.8.5"
description = "Async http client/server framework (asyncio)"
optional = false
python-versions = ">=3.6"
files = [
{file = "aiohttp-3.8.5-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:a94159871304770da4dd371f4291b20cac04e8c94f11bdea1c3478e557fbe0d8"},
{file = "aiohttp-3.8.5-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:13bf85afc99ce6f9ee3567b04501f18f9f8dbbb2ea11ed1a2e079670403a7c84"},
{file = "aiohttp-3.8.5-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2ce2ac5708501afc4847221a521f7e4b245abf5178cf5ddae9d5b3856ddb2f3a"},
{file = "aiohttp-3.8.5-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:96943e5dcc37a6529d18766597c491798b7eb7a61d48878611298afc1fca946c"},
{file = "aiohttp-3.8.5-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2ad5c3c4590bb3cc28b4382f031f3783f25ec223557124c68754a2231d989e2b"},
{file = "aiohttp-3.8.5-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0c413c633d0512df4dc7fd2373ec06cc6a815b7b6d6c2f208ada7e9e93a5061d"},
{file = "aiohttp-3.8.5-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:df72ac063b97837a80d80dec8d54c241af059cc9bb42c4de68bd5b61ceb37caa"},
{file = "aiohttp-3.8.5-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c48c5c0271149cfe467c0ff8eb941279fd6e3f65c9a388c984e0e6cf57538e14"},
{file = "aiohttp-3.8.5-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:368a42363c4d70ab52c2c6420a57f190ed3dfaca6a1b19afda8165ee16416a82"},
{file = "aiohttp-3.8.5-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:7607ec3ce4993464368505888af5beb446845a014bc676d349efec0e05085905"},
{file = "aiohttp-3.8.5-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:0d21c684808288a98914e5aaf2a7c6a3179d4df11d249799c32d1808e79503b5"},
{file = "aiohttp-3.8.5-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:312fcfbacc7880a8da0ae8b6abc6cc7d752e9caa0051a53d217a650b25e9a691"},
{file = "aiohttp-3.8.5-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:ad093e823df03bb3fd37e7dec9d4670c34f9e24aeace76808fc20a507cace825"},
{file = "aiohttp-3.8.5-cp310-cp310-win32.whl", hash = "sha256:33279701c04351a2914e1100b62b2a7fdb9a25995c4a104259f9a5ead7ed4802"},
{file = "aiohttp-3.8.5-cp310-cp310-win_amd64.whl", hash = "sha256:6e4a280e4b975a2e7745573e3fc9c9ba0d1194a3738ce1cbaa80626cc9b4f4df"},
{file = "aiohttp-3.8.5-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:ae871a964e1987a943d83d6709d20ec6103ca1eaf52f7e0d36ee1b5bebb8b9b9"},
{file = "aiohttp-3.8.5-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:461908b2578955045efde733719d62f2b649c404189a09a632d245b445c9c975"},
{file = "aiohttp-3.8.5-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:72a860c215e26192379f57cae5ab12b168b75db8271f111019509a1196dfc780"},
{file = "aiohttp-3.8.5-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cc14be025665dba6202b6a71cfcdb53210cc498e50068bc088076624471f8bb9"},
{file = "aiohttp-3.8.5-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8af740fc2711ad85f1a5c034a435782fbd5b5f8314c9a3ef071424a8158d7f6b"},
{file = "aiohttp-3.8.5-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:841cd8233cbd2111a0ef0a522ce016357c5e3aff8a8ce92bcfa14cef890d698f"},
{file = "aiohttp-3.8.5-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5ed1c46fb119f1b59304b5ec89f834f07124cd23ae5b74288e364477641060ff"},
{file = "aiohttp-3.8.5-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:84f8ae3e09a34f35c18fa57f015cc394bd1389bce02503fb30c394d04ee6b938"},
{file = "aiohttp-3.8.5-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:62360cb771707cb70a6fd114b9871d20d7dd2163a0feafe43fd115cfe4fe845e"},
{file = "aiohttp-3.8.5-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:23fb25a9f0a1ca1f24c0a371523546366bb642397c94ab45ad3aedf2941cec6a"},
{file = "aiohttp-3.8.5-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:b0ba0d15164eae3d878260d4c4df859bbdc6466e9e6689c344a13334f988bb53"},
{file = "aiohttp-3.8.5-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:5d20003b635fc6ae3f96d7260281dfaf1894fc3aa24d1888a9b2628e97c241e5"},
{file = "aiohttp-3.8.5-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:0175d745d9e85c40dcc51c8f88c74bfbaef9e7afeeeb9d03c37977270303064c"},
{file = "aiohttp-3.8.5-cp311-cp311-win32.whl", hash = "sha256:2e1b1e51b0774408f091d268648e3d57f7260c1682e7d3a63cb00d22d71bb945"},
{file = "aiohttp-3.8.5-cp311-cp311-win_amd64.whl", hash = "sha256:043d2299f6dfdc92f0ac5e995dfc56668e1587cea7f9aa9d8a78a1b6554e5755"},
{file = "aiohttp-3.8.5-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:cae533195e8122584ec87531d6df000ad07737eaa3c81209e85c928854d2195c"},
{file = "aiohttp-3.8.5-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4f21e83f355643c345177a5d1d8079f9f28b5133bcd154193b799d380331d5d3"},
{file = "aiohttp-3.8.5-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a7a75ef35f2df54ad55dbf4b73fe1da96f370e51b10c91f08b19603c64004acc"},
{file = "aiohttp-3.8.5-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2e2e9839e14dd5308ee773c97115f1e0a1cb1d75cbeeee9f33824fa5144c7634"},
{file = "aiohttp-3.8.5-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c44e65da1de4403d0576473e2344828ef9c4c6244d65cf4b75549bb46d40b8dd"},
{file = "aiohttp-3.8.5-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:78d847e4cde6ecc19125ccbc9bfac4a7ab37c234dd88fbb3c5c524e8e14da543"},
{file = "aiohttp-3.8.5-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:c7a815258e5895d8900aec4454f38dca9aed71085f227537208057853f9d13f2"},
{file = "aiohttp-3.8.5-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:8b929b9bd7cd7c3939f8bcfffa92fae7480bd1aa425279d51a89327d600c704d"},
{file = "aiohttp-3.8.5-cp36-cp36m-musllinux_1_1_ppc64le.whl", hash = "sha256:5db3a5b833764280ed7618393832e0853e40f3d3e9aa128ac0ba0f8278d08649"},
{file = "aiohttp-3.8.5-cp36-cp36m-musllinux_1_1_s390x.whl", hash = "sha256:a0215ce6041d501f3155dc219712bc41252d0ab76474615b9700d63d4d9292af"},
{file = "aiohttp-3.8.5-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:fd1ed388ea7fbed22c4968dd64bab0198de60750a25fe8c0c9d4bef5abe13824"},
{file = "aiohttp-3.8.5-cp36-cp36m-win32.whl", hash = "sha256:6e6783bcc45f397fdebc118d772103d751b54cddf5b60fbcc958382d7dd64f3e"},
{file = "aiohttp-3.8.5-cp36-cp36m-win_amd64.whl", hash = "sha256:b5411d82cddd212644cf9360879eb5080f0d5f7d809d03262c50dad02f01421a"},
{file = "aiohttp-3.8.5-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:01d4c0c874aa4ddfb8098e85d10b5e875a70adc63db91f1ae65a4b04d3344cda"},
{file = "aiohttp-3.8.5-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e5980a746d547a6ba173fd5ee85ce9077e72d118758db05d229044b469d9029a"},
{file = "aiohttp-3.8.5-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2a482e6da906d5e6e653be079b29bc173a48e381600161c9932d89dfae5942ef"},
{file = "aiohttp-3.8.5-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:80bd372b8d0715c66c974cf57fe363621a02f359f1ec81cba97366948c7fc873"},
{file = "aiohttp-3.8.5-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c1161b345c0a444ebcf46bf0a740ba5dcf50612fd3d0528883fdc0eff578006a"},
{file = "aiohttp-3.8.5-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cd56db019015b6acfaaf92e1ac40eb8434847d9bf88b4be4efe5bfd260aee692"},
{file = "aiohttp-3.8.5-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:153c2549f6c004d2754cc60603d4668899c9895b8a89397444a9c4efa282aaf4"},
{file = "aiohttp-3.8.5-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:4a01951fabc4ce26ab791da5f3f24dca6d9a6f24121746eb19756416ff2d881b"},
{file = "aiohttp-3.8.5-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:bfb9162dcf01f615462b995a516ba03e769de0789de1cadc0f916265c257e5d8"},
{file = "aiohttp-3.8.5-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:7dde0009408969a43b04c16cbbe252c4f5ef4574ac226bc8815cd7342d2028b6"},
{file = "aiohttp-3.8.5-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:4149d34c32f9638f38f544b3977a4c24052042affa895352d3636fa8bffd030a"},
{file = "aiohttp-3.8.5-cp37-cp37m-win32.whl", hash = "sha256:68c5a82c8779bdfc6367c967a4a1b2aa52cd3595388bf5961a62158ee8a59e22"},
{file = "aiohttp-3.8.5-cp37-cp37m-win_amd64.whl", hash = "sha256:2cf57fb50be5f52bda004b8893e63b48530ed9f0d6c96c84620dc92fe3cd9b9d"},
{file = "aiohttp-3.8.5-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:eca4bf3734c541dc4f374ad6010a68ff6c6748f00451707f39857f429ca36ced"},
{file = "aiohttp-3.8.5-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1274477e4c71ce8cfe6c1ec2f806d57c015ebf84d83373676036e256bc55d690"},
{file = "aiohttp-3.8.5-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:28c543e54710d6158fc6f439296c7865b29e0b616629767e685a7185fab4a6b9"},
{file = "aiohttp-3.8.5-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:910bec0c49637d213f5d9877105d26e0c4a4de2f8b1b29405ff37e9fc0ad52b8"},
{file = "aiohttp-3.8.5-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5443910d662db951b2e58eb70b0fbe6b6e2ae613477129a5805d0b66c54b6cb7"},
{file = "aiohttp-3.8.5-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2e460be6978fc24e3df83193dc0cc4de46c9909ed92dd47d349a452ef49325b7"},
{file = "aiohttp-3.8.5-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fb1558def481d84f03b45888473fc5a1f35747b5f334ef4e7a571bc0dfcb11f8"},
{file = "aiohttp-3.8.5-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:34dd0c107799dcbbf7d48b53be761a013c0adf5571bf50c4ecad5643fe9cfcd0"},
{file = "aiohttp-3.8.5-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:aa1990247f02a54185dc0dff92a6904521172a22664c863a03ff64c42f9b5410"},
{file = "aiohttp-3.8.5-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:0e584a10f204a617d71d359fe383406305a4b595b333721fa50b867b4a0a1548"},
{file = "aiohttp-3.8.5-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:a3cf433f127efa43fee6b90ea4c6edf6c4a17109d1d037d1a52abec84d8f2e42"},
{file = "aiohttp-3.8.5-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:c11f5b099adafb18e65c2c997d57108b5bbeaa9eeee64a84302c0978b1ec948b"},
{file = "aiohttp-3.8.5-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:84de26ddf621d7ac4c975dbea4c945860e08cccde492269db4e1538a6a6f3c35"},
{file = "aiohttp-3.8.5-cp38-cp38-win32.whl", hash = "sha256:ab88bafedc57dd0aab55fa728ea10c1911f7e4d8b43e1d838a1739f33712921c"},
{file = "aiohttp-3.8.5-cp38-cp38-win_amd64.whl", hash = "sha256:5798a9aad1879f626589f3df0f8b79b3608a92e9beab10e5fda02c8a2c60db2e"},
{file = "aiohttp-3.8.5-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:a6ce61195c6a19c785df04e71a4537e29eaa2c50fe745b732aa937c0c77169f3"},
{file = "aiohttp-3.8.5-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:773dd01706d4db536335fcfae6ea2440a70ceb03dd3e7378f3e815b03c97ab51"},
{file = "aiohttp-3.8.5-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:f83a552443a526ea38d064588613aca983d0ee0038801bc93c0c916428310c28"},
{file = "aiohttp-3.8.5-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1f7372f7341fcc16f57b2caded43e81ddd18df53320b6f9f042acad41f8e049a"},
{file = "aiohttp-3.8.5-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ea353162f249c8097ea63c2169dd1aa55de1e8fecbe63412a9bc50816e87b761"},
{file = "aiohttp-3.8.5-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e5d47ae48db0b2dcf70bc8a3bc72b3de86e2a590fc299fdbbb15af320d2659de"},
{file = "aiohttp-3.8.5-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d827176898a2b0b09694fbd1088c7a31836d1a505c243811c87ae53a3f6273c1"},
{file = "aiohttp-3.8.5-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3562b06567c06439d8b447037bb655ef69786c590b1de86c7ab81efe1c9c15d8"},
{file = "aiohttp-3.8.5-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:4e874cbf8caf8959d2adf572a78bba17cb0e9d7e51bb83d86a3697b686a0ab4d"},
{file = "aiohttp-3.8.5-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:6809a00deaf3810e38c628e9a33271892f815b853605a936e2e9e5129762356c"},
{file = "aiohttp-3.8.5-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:33776e945d89b29251b33a7e7d006ce86447b2cfd66db5e5ded4e5cd0340585c"},
{file = "aiohttp-3.8.5-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:eaeed7abfb5d64c539e2db173f63631455f1196c37d9d8d873fc316470dfbacd"},
{file = "aiohttp-3.8.5-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:e91d635961bec2d8f19dfeb41a539eb94bd073f075ca6dae6c8dc0ee89ad6f91"},
{file = "aiohttp-3.8.5-cp39-cp39-win32.whl", hash = "sha256:00ad4b6f185ec67f3e6562e8a1d2b69660be43070bd0ef6fcec5211154c7df67"},
{file = "aiohttp-3.8.5-cp39-cp39-win_amd64.whl", hash = "sha256:c0a9034379a37ae42dea7ac1e048352d96286626251862e448933c0f59cbd79c"},
{file = "aiohttp-3.8.5.tar.gz", hash = "sha256:b9552ec52cc147dbf1944ac7ac98af7602e51ea2dcd076ed194ca3c0d1c7d0bc"},
]
[package.dependencies]
aiosignal = ">=1.1.2"
async-timeout = ">=4.0.0a3,<5.0"
attrs = ">=17.3.0"
charset-normalizer = ">=2.0,<4.0"
frozenlist = ">=1.1.1"
multidict = ">=4.5,<7.0"
yarl = ">=1.0,<2.0"
[package.extras]
speedups = ["Brotli", "aiodns", "cchardet"]
[[package]]
name = "aiosignal"
version = "1.3.1"
description = "aiosignal: a list of registered asynchronous callbacks"
optional = false
python-versions = ">=3.7"
files = [
{file = "aiosignal-1.3.1-py3-none-any.whl", hash = "sha256:f8376fb07dd1e86a584e4fcdec80b36b7f81aac666ebc724e2c090300dd83b17"},
{file = "aiosignal-1.3.1.tar.gz", hash = "sha256:54cd96e15e1649b75d6c87526a6ff0b6c1b0dd3459f43d9ca11d48c339b68cfc"},
]
[package.dependencies]
frozenlist = ">=1.1.0"
[[package]]
name = "async-timeout"
version = "4.0.3"
description = "Timeout context manager for asyncio programs"
optional = false
python-versions = ">=3.7"
files = [
{file = "async-timeout-4.0.3.tar.gz", hash = "sha256:4640d96be84d82d02ed59ea2b7105a0f7b33abe8703703cd0ab0bf87c427522f"},
{file = "async_timeout-4.0.3-py3-none-any.whl", hash = "sha256:7405140ff1230c310e51dc27b3145b9092d659ce68ff733fb0cefe3ee42be028"},
]
[[package]]
name = "attrs"
version = "23.1.0"
description = "Classes Without Boilerplate"
optional = false
python-versions = ">=3.7"
files = [
{file = "attrs-23.1.0-py3-none-any.whl", hash = "sha256:1f28b4522cdc2fb4256ac1a020c78acf9cba2c6b461ccd2c126f3aa8e8335d04"},
{file = "attrs-23.1.0.tar.gz", hash = "sha256:6279836d581513a26f1bf235f9acd333bc9115683f14f7e8fae46c98fc50e015"},
]
[package.extras]
cov = ["attrs[tests]", "coverage[toml] (>=5.3)"]
dev = ["attrs[docs,tests]", "pre-commit"]
docs = ["furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphinxcontrib-towncrier", "towncrier", "zope-interface"]
tests = ["attrs[tests-no-zope]", "zope-interface"]
tests-no-zope = ["cloudpickle", "hypothesis", "mypy (>=1.1.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
[[package]]
name = "certifi"
version = "2023.7.22"
description = "Python package for providing Mozilla's CA Bundle."
optional = false
python-versions = ">=3.6"
files = [
{file = "certifi-2023.7.22-py3-none-any.whl", hash = "sha256:92d6037539857d8206b8f6ae472e8b77db8058fec5937a1ef3f54304089edbb9"},
{file = "certifi-2023.7.22.tar.gz", hash = "sha256:539cc1d13202e33ca466e88b2807e29f4c13049d6d87031a3c110744495cb082"},
]
[[package]]
name = "charset-normalizer"
version = "3.2.0"
description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
optional = false
python-versions = ">=3.7.0"
files = [
{file = "charset-normalizer-3.2.0.tar.gz", hash = "sha256:3bb3d25a8e6c0aedd251753a79ae98a093c7e7b471faa3aa9a93a81431987ace"},
{file = "charset_normalizer-3.2.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:0b87549028f680ca955556e3bd57013ab47474c3124dc069faa0b6545b6c9710"},
{file = "charset_normalizer-3.2.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:7c70087bfee18a42b4040bb9ec1ca15a08242cf5867c58726530bdf3945672ed"},
{file = "charset_normalizer-3.2.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a103b3a7069b62f5d4890ae1b8f0597618f628b286b03d4bc9195230b154bfa9"},
{file = "charset_normalizer-3.2.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:94aea8eff76ee6d1cdacb07dd2123a68283cb5569e0250feab1240058f53b623"},
{file = "charset_normalizer-3.2.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:db901e2ac34c931d73054d9797383d0f8009991e723dab15109740a63e7f902a"},
{file = "charset_normalizer-3.2.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b0dac0ff919ba34d4df1b6131f59ce95b08b9065233446be7e459f95554c0dc8"},
{file = "charset_normalizer-3.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:193cbc708ea3aca45e7221ae58f0fd63f933753a9bfb498a3b474878f12caaad"},
{file = "charset_normalizer-3.2.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:09393e1b2a9461950b1c9a45d5fd251dc7c6f228acab64da1c9c0165d9c7765c"},
{file = "charset_normalizer-3.2.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:baacc6aee0b2ef6f3d308e197b5d7a81c0e70b06beae1f1fcacffdbd124fe0e3"},
{file = "charset_normalizer-3.2.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:bf420121d4c8dce6b889f0e8e4ec0ca34b7f40186203f06a946fa0276ba54029"},
{file = "charset_normalizer-3.2.0-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:c04a46716adde8d927adb9457bbe39cf473e1e2c2f5d0a16ceb837e5d841ad4f"},
{file = "charset_normalizer-3.2.0-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:aaf63899c94de41fe3cf934601b0f7ccb6b428c6e4eeb80da72c58eab077b19a"},
{file = "charset_normalizer-3.2.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:d62e51710986674142526ab9f78663ca2b0726066ae26b78b22e0f5e571238dd"},
{file = "charset_normalizer-3.2.0-cp310-cp310-win32.whl", hash = "sha256:04e57ab9fbf9607b77f7d057974694b4f6b142da9ed4a199859d9d4d5c63fe96"},
{file = "charset_normalizer-3.2.0-cp310-cp310-win_amd64.whl", hash = "sha256:48021783bdf96e3d6de03a6e39a1171ed5bd7e8bb93fc84cc649d11490f87cea"},
{file = "charset_normalizer-3.2.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:4957669ef390f0e6719db3613ab3a7631e68424604a7b448f079bee145da6e09"},
{file = "charset_normalizer-3.2.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:46fb8c61d794b78ec7134a715a3e564aafc8f6b5e338417cb19fe9f57a5a9bf2"},
{file = "charset_normalizer-3.2.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f779d3ad205f108d14e99bb3859aa7dd8e9c68874617c72354d7ecaec2a054ac"},
{file = "charset_normalizer-3.2.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f25c229a6ba38a35ae6e25ca1264621cc25d4d38dca2942a7fce0b67a4efe918"},
{file = "charset_normalizer-3.2.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2efb1bd13885392adfda4614c33d3b68dee4921fd0ac1d3988f8cbb7d589e72a"},
{file = "charset_normalizer-3.2.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1f30b48dd7fa1474554b0b0f3fdfdd4c13b5c737a3c6284d3cdc424ec0ffff3a"},
{file = "charset_normalizer-3.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:246de67b99b6851627d945db38147d1b209a899311b1305dd84916f2b88526c6"},
{file = "charset_normalizer-3.2.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9bd9b3b31adcb054116447ea22caa61a285d92e94d710aa5ec97992ff5eb7cf3"},
{file = "charset_normalizer-3.2.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:8c2f5e83493748286002f9369f3e6607c565a6a90425a3a1fef5ae32a36d749d"},
{file = "charset_normalizer-3.2.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:3170c9399da12c9dc66366e9d14da8bf7147e1e9d9ea566067bbce7bb74bd9c2"},
{file = "charset_normalizer-3.2.0-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:7a4826ad2bd6b07ca615c74ab91f32f6c96d08f6fcc3902ceeedaec8cdc3bcd6"},
{file = "charset_normalizer-3.2.0-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:3b1613dd5aee995ec6d4c69f00378bbd07614702a315a2cf6c1d21461fe17c23"},
{file = "charset_normalizer-3.2.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:9e608aafdb55eb9f255034709e20d5a83b6d60c054df0802fa9c9883d0a937aa"},
{file = "charset_normalizer-3.2.0-cp311-cp311-win32.whl", hash = "sha256:f2a1d0fd4242bd8643ce6f98927cf9c04540af6efa92323e9d3124f57727bfc1"},
{file = "charset_normalizer-3.2.0-cp311-cp311-win_amd64.whl", hash = "sha256:681eb3d7e02e3c3655d1b16059fbfb605ac464c834a0c629048a30fad2b27489"},
{file = "charset_normalizer-3.2.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:c57921cda3a80d0f2b8aec7e25c8aa14479ea92b5b51b6876d975d925a2ea346"},
{file = "charset_normalizer-3.2.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:41b25eaa7d15909cf3ac4c96088c1f266a9a93ec44f87f1d13d4a0e86c81b982"},
{file = "charset_normalizer-3.2.0-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f058f6963fd82eb143c692cecdc89e075fa0828db2e5b291070485390b2f1c9c"},
{file = "charset_normalizer-3.2.0-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a7647ebdfb9682b7bb97e2a5e7cb6ae735b1c25008a70b906aecca294ee96cf4"},
{file = "charset_normalizer-3.2.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:eef9df1eefada2c09a5e7a40991b9fc6ac6ef20b1372abd48d2794a316dc0449"},
{file = "charset_normalizer-3.2.0-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e03b8895a6990c9ab2cdcd0f2fe44088ca1c65ae592b8f795c3294af00a461c3"},
{file = "charset_normalizer-3.2.0-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:ee4006268ed33370957f55bf2e6f4d263eaf4dc3cfc473d1d90baff6ed36ce4a"},
{file = "charset_normalizer-3.2.0-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:c4983bf937209c57240cff65906b18bb35e64ae872da6a0db937d7b4af845dd7"},
{file = "charset_normalizer-3.2.0-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:3bb7fda7260735efe66d5107fb7e6af6a7c04c7fce9b2514e04b7a74b06bf5dd"},
{file = "charset_normalizer-3.2.0-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:72814c01533f51d68702802d74f77ea026b5ec52793c791e2da806a3844a46c3"},
{file = "charset_normalizer-3.2.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:70c610f6cbe4b9fce272c407dd9d07e33e6bf7b4aa1b7ffb6f6ded8e634e3592"},
{file = "charset_normalizer-3.2.0-cp37-cp37m-win32.whl", hash = "sha256:a401b4598e5d3f4a9a811f3daf42ee2291790c7f9d74b18d75d6e21dda98a1a1"},
{file = "charset_normalizer-3.2.0-cp37-cp37m-win_amd64.whl", hash = "sha256:c0b21078a4b56965e2b12f247467b234734491897e99c1d51cee628da9786959"},
{file = "charset_normalizer-3.2.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:95eb302ff792e12aba9a8b8f8474ab229a83c103d74a750ec0bd1c1eea32e669"},
{file = "charset_normalizer-3.2.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1a100c6d595a7f316f1b6f01d20815d916e75ff98c27a01ae817439ea7726329"},
{file = "charset_normalizer-3.2.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:6339d047dab2780cc6220f46306628e04d9750f02f983ddb37439ca47ced7149"},
{file = "charset_normalizer-3.2.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e4b749b9cc6ee664a3300bb3a273c1ca8068c46be705b6c31cf5d276f8628a94"},
{file = "charset_normalizer-3.2.0-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a38856a971c602f98472050165cea2cdc97709240373041b69030be15047691f"},
{file = "charset_normalizer-3.2.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f87f746ee241d30d6ed93969de31e5ffd09a2961a051e60ae6bddde9ec3583aa"},
{file = "charset_normalizer-3.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:89f1b185a01fe560bc8ae5f619e924407efca2191b56ce749ec84982fc59a32a"},
{file = "charset_normalizer-3.2.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e1c8a2f4c69e08e89632defbfabec2feb8a8d99edc9f89ce33c4b9e36ab63037"},
{file = "charset_normalizer-3.2.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:2f4ac36d8e2b4cc1aa71df3dd84ff8efbe3bfb97ac41242fbcfc053c67434f46"},
{file = "charset_normalizer-3.2.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:a386ebe437176aab38c041de1260cd3ea459c6ce5263594399880bbc398225b2"},
{file = "charset_normalizer-3.2.0-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:ccd16eb18a849fd8dcb23e23380e2f0a354e8daa0c984b8a732d9cfaba3a776d"},
{file = "charset_normalizer-3.2.0-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:e6a5bf2cba5ae1bb80b154ed68a3cfa2fa00fde979a7f50d6598d3e17d9ac20c"},
{file = "charset_normalizer-3.2.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:45de3f87179c1823e6d9e32156fb14c1927fcc9aba21433f088fdfb555b77c10"},
{file = "charset_normalizer-3.2.0-cp38-cp38-win32.whl", hash = "sha256:1000fba1057b92a65daec275aec30586c3de2401ccdcd41f8a5c1e2c87078706"},
{file = "charset_normalizer-3.2.0-cp38-cp38-win_amd64.whl", hash = "sha256:8b2c760cfc7042b27ebdb4a43a4453bd829a5742503599144d54a032c5dc7e9e"},
{file = "charset_normalizer-3.2.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:855eafa5d5a2034b4621c74925d89c5efef61418570e5ef9b37717d9c796419c"},
{file = "charset_normalizer-3.2.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:203f0c8871d5a7987be20c72442488a0b8cfd0f43b7973771640fc593f56321f"},
{file = "charset_normalizer-3.2.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e857a2232ba53ae940d3456f7533ce6ca98b81917d47adc3c7fd55dad8fab858"},
{file = "charset_normalizer-3.2.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5e86d77b090dbddbe78867a0275cb4df08ea195e660f1f7f13435a4649e954e5"},
{file = "charset_normalizer-3.2.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c4fb39a81950ec280984b3a44f5bd12819953dc5fa3a7e6fa7a80db5ee853952"},
{file = "charset_normalizer-3.2.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2dee8e57f052ef5353cf608e0b4c871aee320dd1b87d351c28764fc0ca55f9f4"},
{file = "charset_normalizer-3.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8700f06d0ce6f128de3ccdbc1acaea1ee264d2caa9ca05daaf492fde7c2a7200"},
{file = "charset_normalizer-3.2.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1920d4ff15ce893210c1f0c0e9d19bfbecb7983c76b33f046c13a8ffbd570252"},
{file = "charset_normalizer-3.2.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:c1c76a1743432b4b60ab3358c937a3fe1341c828ae6194108a94c69028247f22"},
{file = "charset_normalizer-3.2.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:f7560358a6811e52e9c4d142d497f1a6e10103d3a6881f18d04dbce3729c0e2c"},
{file = "charset_normalizer-3.2.0-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:c8063cf17b19661471ecbdb3df1c84f24ad2e389e326ccaf89e3fb2484d8dd7e"},
{file = "charset_normalizer-3.2.0-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:cd6dbe0238f7743d0efe563ab46294f54f9bc8f4b9bcf57c3c666cc5bc9d1299"},
{file = "charset_normalizer-3.2.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:1249cbbf3d3b04902ff081ffbb33ce3377fa6e4c7356f759f3cd076cc138d020"},
{file = "charset_normalizer-3.2.0-cp39-cp39-win32.whl", hash = "sha256:6c409c0deba34f147f77efaa67b8e4bb83d2f11c8806405f76397ae5b8c0d1c9"},
{file = "charset_normalizer-3.2.0-cp39-cp39-win_amd64.whl", hash = "sha256:7095f6fbfaa55defb6b733cfeb14efaae7a29f0b59d8cf213be4e7ca0b857b80"},
{file = "charset_normalizer-3.2.0-py3-none-any.whl", hash = "sha256:8e098148dd37b4ce3baca71fb394c81dc5d9c7728c95df695d2dca218edf40e6"},
]
[[package]]
name = "colorama"
version = "0.4.6"
description = "Cross-platform colored terminal text."
optional = false
python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,>=2.7"
files = [
{file = "colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6"},
{file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
]
[[package]]
name = "colored"
version = "1.4.4"
description = "Simple library for color and formatting to terminal"
optional = false
python-versions = "*"
files = [
{file = "colored-1.4.4.tar.gz", hash = "sha256:04ff4d4dd514274fe3b99a21bb52fb96f2688c01e93fba7bef37221e7cb56ce0"},
]
[[package]]
name = "docker"
version = "6.1.3"
description = "A Python library for the Docker Engine API."
optional = false
python-versions = ">=3.7"
files = [
{file = "docker-6.1.3-py3-none-any.whl", hash = "sha256:aecd2277b8bf8e506e484f6ab7aec39abe0038e29fa4a6d3ba86c3fe01844ed9"},
{file = "docker-6.1.3.tar.gz", hash = "sha256:aa6d17830045ba5ef0168d5eaa34d37beeb113948c413affe1d5991fc11f9a20"},
]
[package.dependencies]
packaging = ">=14.0"
pywin32 = {version = ">=304", markers = "sys_platform == \"win32\""}
requests = ">=2.26.0"
urllib3 = ">=1.26.0"
websocket-client = ">=0.32.0"
[package.extras]
ssh = ["paramiko (>=2.4.3)"]
[[package]]
name = "exceptiongroup"
version = "1.1.3"
description = "Backport of PEP 654 (exception groups)"
optional = false
python-versions = ">=3.7"
files = [
{file = "exceptiongroup-1.1.3-py3-none-any.whl", hash = "sha256:343280667a4585d195ca1cf9cef84a4e178c4b6cf2274caef9859782b567d5e3"},
{file = "exceptiongroup-1.1.3.tar.gz", hash = "sha256:097acd85d473d75af5bb98e41b61ff7fe35efe6675e4f9370ec6ec5126d160e9"},
]
[package.extras]
test = ["pytest (>=6)"]
[[package]]
name = "filelock"
version = "3.12.3"
description = "A platform independent file lock."
optional = false
python-versions = ">=3.8"
files = [
{file = "filelock-3.12.3-py3-none-any.whl", hash = "sha256:f067e40ccc40f2b48395a80fcbd4728262fab54e232e090a4063ab804179efeb"},
{file = "filelock-3.12.3.tar.gz", hash = "sha256:0ecc1dd2ec4672a10c8550a8182f1bd0c0a5088470ecd5a125e45f49472fac3d"},
]
[package.dependencies]
typing-extensions = {version = ">=4.7.1", markers = "python_version < \"3.11\""}
[package.extras]
docs = ["furo (>=2023.7.26)", "sphinx (>=7.1.2)", "sphinx-autodoc-typehints (>=1.24)"]
testing = ["covdefaults (>=2.3)", "coverage (>=7.3)", "diff-cover (>=7.7)", "pytest (>=7.4)", "pytest-cov (>=4.1)", "pytest-mock (>=3.11.1)", "pytest-timeout (>=2.1)"]
[[package]]
name = "frozenlist"
version = "1.4.0"
description = "A list-like structure which implements collections.abc.MutableSequence"
optional = false
python-versions = ">=3.8"
files = [
{file = "frozenlist-1.4.0-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:764226ceef3125e53ea2cb275000e309c0aa5464d43bd72abd661e27fffc26ab"},
{file = "frozenlist-1.4.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d6484756b12f40003c6128bfcc3fa9f0d49a687e171186c2d85ec82e3758c559"},
{file = "frozenlist-1.4.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9ac08e601308e41eb533f232dbf6b7e4cea762f9f84f6357136eed926c15d12c"},
{file = "frozenlist-1.4.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d081f13b095d74b67d550de04df1c756831f3b83dc9881c38985834387487f1b"},
{file = "frozenlist-1.4.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:71932b597f9895f011f47f17d6428252fc728ba2ae6024e13c3398a087c2cdea"},
{file = "frozenlist-1.4.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:981b9ab5a0a3178ff413bca62526bb784249421c24ad7381e39d67981be2c326"},
{file = "frozenlist-1.4.0-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e41f3de4df3e80de75845d3e743b3f1c4c8613c3997a912dbf0229fc61a8b963"},
{file = "frozenlist-1.4.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6918d49b1f90821e93069682c06ffde41829c346c66b721e65a5c62b4bab0300"},
{file = "frozenlist-1.4.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:0e5c8764c7829343d919cc2dfc587a8db01c4f70a4ebbc49abde5d4b158b007b"},
{file = "frozenlist-1.4.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:8d0edd6b1c7fb94922bf569c9b092ee187a83f03fb1a63076e7774b60f9481a8"},
{file = "frozenlist-1.4.0-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:e29cda763f752553fa14c68fb2195150bfab22b352572cb36c43c47bedba70eb"},
{file = "frozenlist-1.4.0-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:0c7c1b47859ee2cac3846fde1c1dc0f15da6cec5a0e5c72d101e0f83dcb67ff9"},
{file = "frozenlist-1.4.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:901289d524fdd571be1c7be054f48b1f88ce8dddcbdf1ec698b27d4b8b9e5d62"},
{file = "frozenlist-1.4.0-cp310-cp310-win32.whl", hash = "sha256:1a0848b52815006ea6596c395f87449f693dc419061cc21e970f139d466dc0a0"},
{file = "frozenlist-1.4.0-cp310-cp310-win_amd64.whl", hash = "sha256:b206646d176a007466358aa21d85cd8600a415c67c9bd15403336c331a10d956"},
{file = "frozenlist-1.4.0-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:de343e75f40e972bae1ef6090267f8260c1446a1695e77096db6cfa25e759a95"},
{file = "frozenlist-1.4.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:ad2a9eb6d9839ae241701d0918f54c51365a51407fd80f6b8289e2dfca977cc3"},
{file = "frozenlist-1.4.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:bd7bd3b3830247580de99c99ea2a01416dfc3c34471ca1298bccabf86d0ff4dc"},
{file = "frozenlist-1.4.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bdf1847068c362f16b353163391210269e4f0569a3c166bc6a9f74ccbfc7e839"},
{file = "frozenlist-1.4.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:38461d02d66de17455072c9ba981d35f1d2a73024bee7790ac2f9e361ef1cd0c"},
{file = "frozenlist-1.4.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d5a32087d720c608f42caed0ef36d2b3ea61a9d09ee59a5142d6070da9041b8f"},
{file = "frozenlist-1.4.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:dd65632acaf0d47608190a71bfe46b209719bf2beb59507db08ccdbe712f969b"},
{file = "frozenlist-1.4.0-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:261b9f5d17cac914531331ff1b1d452125bf5daa05faf73b71d935485b0c510b"},
{file = "frozenlist-1.4.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:b89ac9768b82205936771f8d2eb3ce88503b1556324c9f903e7156669f521472"},
{file = "frozenlist-1.4.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:008eb8b31b3ea6896da16c38c1b136cb9fec9e249e77f6211d479db79a4eaf01"},
{file = "frozenlist-1.4.0-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:e74b0506fa5aa5598ac6a975a12aa8928cbb58e1f5ac8360792ef15de1aa848f"},
{file = "frozenlist-1.4.0-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:490132667476f6781b4c9458298b0c1cddf237488abd228b0b3650e5ecba7467"},
{file = "frozenlist-1.4.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:76d4711f6f6d08551a7e9ef28c722f4a50dd0fc204c56b4bcd95c6cc05ce6fbb"},
{file = "frozenlist-1.4.0-cp311-cp311-win32.whl", hash = "sha256:a02eb8ab2b8f200179b5f62b59757685ae9987996ae549ccf30f983f40602431"},
{file = "frozenlist-1.4.0-cp311-cp311-win_amd64.whl", hash = "sha256:515e1abc578dd3b275d6a5114030b1330ba044ffba03f94091842852f806f1c1"},
{file = "frozenlist-1.4.0-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:f0ed05f5079c708fe74bf9027e95125334b6978bf07fd5ab923e9e55e5fbb9d3"},
{file = "frozenlist-1.4.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:ca265542ca427bf97aed183c1676e2a9c66942e822b14dc6e5f42e038f92a503"},
{file = "frozenlist-1.4.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:491e014f5c43656da08958808588cc6c016847b4360e327a62cb308c791bd2d9"},
{file = "frozenlist-1.4.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:17ae5cd0f333f94f2e03aaf140bb762c64783935cc764ff9c82dff626089bebf"},
{file = "frozenlist-1.4.0-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1e78fb68cf9c1a6aa4a9a12e960a5c9dfbdb89b3695197aa7064705662515de2"},
{file = "frozenlist-1.4.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d5655a942f5f5d2c9ed93d72148226d75369b4f6952680211972a33e59b1dfdc"},
{file = "frozenlist-1.4.0-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c11b0746f5d946fecf750428a95f3e9ebe792c1ee3b1e96eeba145dc631a9672"},
{file = "frozenlist-1.4.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e66d2a64d44d50d2543405fb183a21f76b3b5fd16f130f5c99187c3fb4e64919"},
{file = "frozenlist-1.4.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:88f7bc0fcca81f985f78dd0fa68d2c75abf8272b1f5c323ea4a01a4d7a614efc"},
{file = "frozenlist-1.4.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:5833593c25ac59ede40ed4de6d67eb42928cca97f26feea219f21d0ed0959b79"},
{file = "frozenlist-1.4.0-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:fec520865f42e5c7f050c2a79038897b1c7d1595e907a9e08e3353293ffc948e"},
{file = "frozenlist-1.4.0-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:b826d97e4276750beca7c8f0f1a4938892697a6bcd8ec8217b3312dad6982781"},
{file = "frozenlist-1.4.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:ceb6ec0a10c65540421e20ebd29083c50e6d1143278746a4ef6bcf6153171eb8"},
{file = "frozenlist-1.4.0-cp38-cp38-win32.whl", hash = "sha256:2b8bcf994563466db019fab287ff390fffbfdb4f905fc77bc1c1d604b1c689cc"},
{file = "frozenlist-1.4.0-cp38-cp38-win_amd64.whl", hash = "sha256:a6c8097e01886188e5be3e6b14e94ab365f384736aa1fca6a0b9e35bd4a30bc7"},
{file = "frozenlist-1.4.0-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:6c38721585f285203e4b4132a352eb3daa19121a035f3182e08e437cface44bf"},
{file = "frozenlist-1.4.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:a0c6da9aee33ff0b1a451e867da0c1f47408112b3391dd43133838339e410963"},
{file = "frozenlist-1.4.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:93ea75c050c5bb3d98016b4ba2497851eadf0ac154d88a67d7a6816206f6fa7f"},
{file = "frozenlist-1.4.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f61e2dc5ad442c52b4887f1fdc112f97caeff4d9e6ebe78879364ac59f1663e1"},
{file = "frozenlist-1.4.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:aa384489fefeb62321b238e64c07ef48398fe80f9e1e6afeff22e140e0850eef"},
{file = "frozenlist-1.4.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:10ff5faaa22786315ef57097a279b833ecab1a0bfb07d604c9cbb1c4cdc2ed87"},
{file = "frozenlist-1.4.0-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:007df07a6e3eb3e33e9a1fe6a9db7af152bbd8a185f9aaa6ece10a3529e3e1c6"},
{file = "frozenlist-1.4.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7f4f399d28478d1f604c2ff9119907af9726aed73680e5ed1ca634d377abb087"},
{file = "frozenlist-1.4.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:c5374b80521d3d3f2ec5572e05adc94601985cc526fb276d0c8574a6d749f1b3"},
{file = "frozenlist-1.4.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:ce31ae3e19f3c902de379cf1323d90c649425b86de7bbdf82871b8a2a0615f3d"},
{file = "frozenlist-1.4.0-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:7211ef110a9194b6042449431e08c4d80c0481e5891e58d429df5899690511c2"},
{file = "frozenlist-1.4.0-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:556de4430ce324c836789fa4560ca62d1591d2538b8ceb0b4f68fb7b2384a27a"},
{file = "frozenlist-1.4.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:7645a8e814a3ee34a89c4a372011dcd817964ce8cb273c8ed6119d706e9613e3"},
{file = "frozenlist-1.4.0-cp39-cp39-win32.whl", hash = "sha256:19488c57c12d4e8095a922f328df3f179c820c212940a498623ed39160bc3c2f"},
{file = "frozenlist-1.4.0-cp39-cp39-win_amd64.whl", hash = "sha256:6221d84d463fb110bdd7619b69cb43878a11d51cbb9394ae3105d082d5199167"},
{file = "frozenlist-1.4.0.tar.gz", hash = "sha256:09163bdf0b2907454042edb19f887c6d33806adc71fbd54afc14908bfdc22251"},
]
[[package]]
name = "fsspec"
version = "2023.6.0"
description = "File-system specification"
optional = false
python-versions = ">=3.8"
files = [
{file = "fsspec-2023.6.0-py3-none-any.whl", hash = "sha256:1cbad1faef3e391fba6dc005ae9b5bdcbf43005c9167ce78c915549c352c869a"},
{file = "fsspec-2023.6.0.tar.gz", hash = "sha256:d0b2f935446169753e7a5c5c55681c54ea91996cc67be93c39a154fb3a2742af"},
]
[package.extras]
abfs = ["adlfs"]
adl = ["adlfs"]
arrow = ["pyarrow (>=1)"]
dask = ["dask", "distributed"]
devel = ["pytest", "pytest-cov"]
dropbox = ["dropbox", "dropboxdrivefs", "requests"]
full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "dask", "distributed", "dropbox", "dropboxdrivefs", "fusepy", "gcsfs", "libarchive-c", "ocifs", "panel", "paramiko", "pyarrow (>=1)", "pygit2", "requests", "s3fs", "smbprotocol", "tqdm"]
fuse = ["fusepy"]
gcs = ["gcsfs"]
git = ["pygit2"]
github = ["requests"]
gs = ["gcsfs"]
gui = ["panel"]
hdfs = ["pyarrow (>=1)"]
http = ["aiohttp (!=4.0.0a0,!=4.0.0a1)", "requests"]
libarchive = ["libarchive-c"]
oci = ["ocifs"]
s3 = ["s3fs"]
sftp = ["paramiko"]
smb = ["smbprotocol"]
ssh = ["paramiko"]
tqdm = ["tqdm"]
[[package]]
name = "huggingface-hub"
version = "0.16.4"
description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
optional = false
python-versions = ">=3.7.0"
files = [
{file = "huggingface_hub-0.16.4-py3-none-any.whl", hash = "sha256:0d3df29932f334fead024afc7cb4cc5149d955238b8b5e42dcf9740d6995a349"},
{file = "huggingface_hub-0.16.4.tar.gz", hash = "sha256:608c7d4f3d368b326d1747f91523dbd1f692871e8e2e7a4750314a2dd8b63e14"},
]
[package.dependencies]
filelock = "*"
fsspec = "*"
packaging = ">=20.9"
pyyaml = ">=5.1"
requests = "*"
tqdm = ">=4.42.1"
typing-extensions = ">=3.7.4.3"
[package.extras]
all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "black (>=23.1,<24.0)", "gradio", "jedi", "mypy (==0.982)", "numpy", "pydantic", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-vcr", "pytest-xdist", "ruff (>=0.0.241)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "urllib3 (<2.0)"]
cli = ["InquirerPy (==0.3.4)"]
dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "black (>=23.1,<24.0)", "gradio", "jedi", "mypy (==0.982)", "numpy", "pydantic", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-vcr", "pytest-xdist", "ruff (>=0.0.241)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "urllib3 (<2.0)"]
fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"]
inference = ["aiohttp", "pydantic"]
quality = ["black (>=23.1,<24.0)", "mypy (==0.982)", "ruff (>=0.0.241)"]
tensorflow = ["graphviz", "pydot", "tensorflow"]
testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "gradio", "jedi", "numpy", "pydantic", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-vcr", "pytest-xdist", "soundfile", "urllib3 (<2.0)"]
torch = ["torch"]
typing = ["pydantic", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
[[package]]
name = "idna"
version = "3.4"
description = "Internationalized Domain Names in Applications (IDNA)"
optional = false
python-versions = ">=3.5"
files = [
{file = "idna-3.4-py3-none-any.whl", hash = "sha256:90b77e79eaa3eba6de819a0c442c0b4ceefc341a7a2ab77d7562bf49f425c5c2"},
{file = "idna-3.4.tar.gz", hash = "sha256:814f528e8dead7d329833b91c5faa87d60bf71824cd12a7530b5526063d02cb4"},
]
[[package]]
name = "iniconfig"
version = "2.0.0"
description = "brain-dead simple config-ini parsing"
optional = false
python-versions = ">=3.7"
files = [
{file = "iniconfig-2.0.0-py3-none-any.whl", hash = "sha256:b6a85871a79d2e3b22d2d1b94ac2824226a63c6b741c88f7ae975f18b6778374"},
{file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"},
]
[[package]]
name = "multidict"
version = "6.0.4"
description = "multidict implementation"
optional = false
python-versions = ">=3.7"
files = [
{file = "multidict-6.0.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:0b1a97283e0c85772d613878028fec909f003993e1007eafa715b24b377cb9b8"},
{file = "multidict-6.0.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:eeb6dcc05e911516ae3d1f207d4b0520d07f54484c49dfc294d6e7d63b734171"},
{file = "multidict-6.0.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:d6d635d5209b82a3492508cf5b365f3446afb65ae7ebd755e70e18f287b0adf7"},
{file = "multidict-6.0.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c048099e4c9e9d615545e2001d3d8a4380bd403e1a0578734e0d31703d1b0c0b"},
{file = "multidict-6.0.4-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ea20853c6dbbb53ed34cb4d080382169b6f4554d394015f1bef35e881bf83547"},
{file = "multidict-6.0.4-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:16d232d4e5396c2efbbf4f6d4df89bfa905eb0d4dc5b3549d872ab898451f569"},
{file = "multidict-6.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:36c63aaa167f6c6b04ef2c85704e93af16c11d20de1d133e39de6a0e84582a93"},
{file = "multidict-6.0.4-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:64bdf1086b6043bf519869678f5f2757f473dee970d7abf6da91ec00acb9cb98"},
{file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:43644e38f42e3af682690876cff722d301ac585c5b9e1eacc013b7a3f7b696a0"},
{file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:7582a1d1030e15422262de9f58711774e02fa80df0d1578995c76214f6954988"},
{file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:ddff9c4e225a63a5afab9dd15590432c22e8057e1a9a13d28ed128ecf047bbdc"},
{file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:ee2a1ece51b9b9e7752e742cfb661d2a29e7bcdba2d27e66e28a99f1890e4fa0"},
{file = "multidict-6.0.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a2e4369eb3d47d2034032a26c7a80fcb21a2cb22e1173d761a162f11e562caa5"},
{file = "multidict-6.0.4-cp310-cp310-win32.whl", hash = "sha256:574b7eae1ab267e5f8285f0fe881f17efe4b98c39a40858247720935b893bba8"},
{file = "multidict-6.0.4-cp310-cp310-win_amd64.whl", hash = "sha256:4dcbb0906e38440fa3e325df2359ac6cb043df8e58c965bb45f4e406ecb162cc"},
{file = "multidict-6.0.4-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:0dfad7a5a1e39c53ed00d2dd0c2e36aed4650936dc18fd9a1826a5ae1cad6f03"},
{file = "multidict-6.0.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:64da238a09d6039e3bd39bb3aee9c21a5e34f28bfa5aa22518581f910ff94af3"},
{file = "multidict-6.0.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:ff959bee35038c4624250473988b24f846cbeb2c6639de3602c073f10410ceba"},
{file = "multidict-6.0.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:01a3a55bd90018c9c080fbb0b9f4891db37d148a0a18722b42f94694f8b6d4c9"},
{file = "multidict-6.0.4-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c5cb09abb18c1ea940fb99360ea0396f34d46566f157122c92dfa069d3e0e982"},
{file = "multidict-6.0.4-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:666daae833559deb2d609afa4490b85830ab0dfca811a98b70a205621a6109fe"},
{file = "multidict-6.0.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:11bdf3f5e1518b24530b8241529d2050014c884cf18b6fc69c0c2b30ca248710"},
{file = "multidict-6.0.4-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7d18748f2d30f94f498e852c67d61261c643b349b9d2a581131725595c45ec6c"},
{file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:458f37be2d9e4c95e2d8866a851663cbc76e865b78395090786f6cd9b3bbf4f4"},
{file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:b1a2eeedcead3a41694130495593a559a668f382eee0727352b9a41e1c45759a"},
{file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:7d6ae9d593ef8641544d6263c7fa6408cc90370c8cb2bbb65f8d43e5b0351d9c"},
{file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:5979b5632c3e3534e42ca6ff856bb24b2e3071b37861c2c727ce220d80eee9ed"},
{file = "multidict-6.0.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:dcfe792765fab89c365123c81046ad4103fcabbc4f56d1c1997e6715e8015461"},
{file = "multidict-6.0.4-cp311-cp311-win32.whl", hash = "sha256:3601a3cece3819534b11d4efc1eb76047488fddd0c85a3948099d5da4d504636"},
{file = "multidict-6.0.4-cp311-cp311-win_amd64.whl", hash = "sha256:81a4f0b34bd92df3da93315c6a59034df95866014ac08535fc819f043bfd51f0"},
{file = "multidict-6.0.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:67040058f37a2a51ed8ea8f6b0e6ee5bd78ca67f169ce6122f3e2ec80dfe9b78"},
{file = "multidict-6.0.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:853888594621e6604c978ce2a0444a1e6e70c8d253ab65ba11657659dcc9100f"},
{file = "multidict-6.0.4-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:39ff62e7d0f26c248b15e364517a72932a611a9b75f35b45be078d81bdb86603"},
{file = "multidict-6.0.4-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:af048912e045a2dc732847d33821a9d84ba553f5c5f028adbd364dd4765092ac"},
{file = "multidict-6.0.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b1e8b901e607795ec06c9e42530788c45ac21ef3aaa11dbd0c69de543bfb79a9"},
{file = "multidict-6.0.4-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:62501642008a8b9871ddfccbf83e4222cf8ac0d5aeedf73da36153ef2ec222d2"},
{file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:99b76c052e9f1bc0721f7541e5e8c05db3941eb9ebe7b8553c625ef88d6eefde"},
{file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:509eac6cf09c794aa27bcacfd4d62c885cce62bef7b2c3e8b2e49d365b5003fe"},
{file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:21a12c4eb6ddc9952c415f24eef97e3e55ba3af61f67c7bc388dcdec1404a067"},
{file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:5cad9430ab3e2e4fa4a2ef4450f548768400a2ac635841bc2a56a2052cdbeb87"},
{file = "multidict-6.0.4-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:ab55edc2e84460694295f401215f4a58597f8f7c9466faec545093045476327d"},
{file = "multidict-6.0.4-cp37-cp37m-win32.whl", hash = "sha256:5a4dcf02b908c3b8b17a45fb0f15b695bf117a67b76b7ad18b73cf8e92608775"},
{file = "multidict-6.0.4-cp37-cp37m-win_amd64.whl", hash = "sha256:6ed5f161328b7df384d71b07317f4d8656434e34591f20552c7bcef27b0ab88e"},
{file = "multidict-6.0.4-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:5fc1b16f586f049820c5c5b17bb4ee7583092fa0d1c4e28b5239181ff9532e0c"},
{file = "multidict-6.0.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1502e24330eb681bdaa3eb70d6358e818e8e8f908a22a1851dfd4e15bc2f8161"},
{file = "multidict-6.0.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:b692f419760c0e65d060959df05f2a531945af31fda0c8a3b3195d4efd06de11"},
{file = "multidict-6.0.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:45e1ecb0379bfaab5eef059f50115b54571acfbe422a14f668fc8c27ba410e7e"},
{file = "multidict-6.0.4-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ddd3915998d93fbcd2566ddf9cf62cdb35c9e093075f862935573d265cf8f65d"},
{file = "multidict-6.0.4-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:59d43b61c59d82f2effb39a93c48b845efe23a3852d201ed2d24ba830d0b4cf2"},
{file = "multidict-6.0.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cc8e1d0c705233c5dd0c5e6460fbad7827d5d36f310a0fadfd45cc3029762258"},
{file = "multidict-6.0.4-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d6aa0418fcc838522256761b3415822626f866758ee0bc6632c9486b179d0b52"},
{file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:6748717bb10339c4760c1e63da040f5f29f5ed6e59d76daee30305894069a660"},
{file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:4d1a3d7ef5e96b1c9e92f973e43aa5e5b96c659c9bc3124acbbd81b0b9c8a951"},
{file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:4372381634485bec7e46718edc71528024fcdc6f835baefe517b34a33c731d60"},
{file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:fc35cb4676846ef752816d5be2193a1e8367b4c1397b74a565a9d0389c433a1d"},
{file = "multidict-6.0.4-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:4b9d9e4e2b37daddb5c23ea33a3417901fa7c7b3dee2d855f63ee67a0b21e5b1"},
{file = "multidict-6.0.4-cp38-cp38-win32.whl", hash = "sha256:e41b7e2b59679edfa309e8db64fdf22399eec4b0b24694e1b2104fb789207779"},
{file = "multidict-6.0.4-cp38-cp38-win_amd64.whl", hash = "sha256:d6c254ba6e45d8e72739281ebc46ea5eb5f101234f3ce171f0e9f5cc86991480"},
{file = "multidict-6.0.4-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:16ab77bbeb596e14212e7bab8429f24c1579234a3a462105cda4a66904998664"},
{file = "multidict-6.0.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:bc779e9e6f7fda81b3f9aa58e3a6091d49ad528b11ed19f6621408806204ad35"},
{file = "multidict-6.0.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:4ceef517eca3e03c1cceb22030a3e39cb399ac86bff4e426d4fc6ae49052cc60"},
{file = "multidict-6.0.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:281af09f488903fde97923c7744bb001a9b23b039a909460d0f14edc7bf59706"},
{file = "multidict-6.0.4-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:52f2dffc8acaba9a2f27174c41c9e57f60b907bb9f096b36b1a1f3be71c6284d"},
{file = "multidict-6.0.4-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b41156839806aecb3641f3208c0dafd3ac7775b9c4c422d82ee2a45c34ba81ca"},
{file = "multidict-6.0.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d5e3fc56f88cc98ef8139255cf8cd63eb2c586531e43310ff859d6bb3a6b51f1"},
{file = "multidict-6.0.4-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8316a77808c501004802f9beebde51c9f857054a0c871bd6da8280e718444449"},
{file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:f70b98cd94886b49d91170ef23ec5c0e8ebb6f242d734ed7ed677b24d50c82cf"},
{file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:bf6774e60d67a9efe02b3616fee22441d86fab4c6d335f9d2051d19d90a40063"},
{file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:e69924bfcdda39b722ef4d9aa762b2dd38e4632b3641b1d9a57ca9cd18f2f83a"},
{file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:6b181d8c23da913d4ff585afd1155a0e1194c0b50c54fcfe286f70cdaf2b7176"},
{file = "multidict-6.0.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:52509b5be062d9eafc8170e53026fbc54cf3b32759a23d07fd935fb04fc22d95"},
{file = "multidict-6.0.4-cp39-cp39-win32.whl", hash = "sha256:27c523fbfbdfd19c6867af7346332b62b586eed663887392cff78d614f9ec313"},
{file = "multidict-6.0.4-cp39-cp39-win_amd64.whl", hash = "sha256:33029f5734336aa0d4c0384525da0387ef89148dc7191aae00ca5fb23d7aafc2"},
{file = "multidict-6.0.4.tar.gz", hash = "sha256:3666906492efb76453c0e7b97f2cf459b0682e7402c0489a95484965dbc1da49"},
]
[[package]]
name = "packaging"
version = "23.1"
description = "Core utilities for Python packages"
optional = false
python-versions = ">=3.7"
files = [
{file = "packaging-23.1-py3-none-any.whl", hash = "sha256:994793af429502c4ea2ebf6bf664629d07c1a9fe974af92966e4b8d2df7edc61"},
{file = "packaging-23.1.tar.gz", hash = "sha256:a392980d2b6cffa644431898be54b0045151319d1e7ec34f0cfed48767dd334f"},
]
[[package]]
name = "pluggy"
version = "1.3.0"
description = "plugin and hook calling mechanisms for python"
optional = false
python-versions = ">=3.8"
files = [
{file = "pluggy-1.3.0-py3-none-any.whl", hash = "sha256:d89c696a773f8bd377d18e5ecda92b7a3793cbe66c87060a6fb58c7b6e1061f7"},
{file = "pluggy-1.3.0.tar.gz", hash = "sha256:cf61ae8f126ac6f7c451172cf30e3e43d3ca77615509771b3a984a0730651e12"},
]
[package.extras]
dev = ["pre-commit", "tox"]
testing = ["pytest", "pytest-benchmark"]
[[package]]
name = "pydantic"
version = "1.10.12"
description = "Data validation and settings management using python type hints"
optional = false
python-versions = ">=3.7"
files = [
{file = "pydantic-1.10.12-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:a1fcb59f2f355ec350073af41d927bf83a63b50e640f4dbaa01053a28b7a7718"},
{file = "pydantic-1.10.12-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:b7ccf02d7eb340b216ec33e53a3a629856afe1c6e0ef91d84a4e6f2fb2ca70fe"},
{file = "pydantic-1.10.12-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8fb2aa3ab3728d950bcc885a2e9eff6c8fc40bc0b7bb434e555c215491bcf48b"},
{file = "pydantic-1.10.12-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:771735dc43cf8383959dc9b90aa281f0b6092321ca98677c5fb6125a6f56d58d"},
{file = "pydantic-1.10.12-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:ca48477862372ac3770969b9d75f1bf66131d386dba79506c46d75e6b48c1e09"},
{file = "pydantic-1.10.12-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a5e7add47a5b5a40c49b3036d464e3c7802f8ae0d1e66035ea16aa5b7a3923ed"},
{file = "pydantic-1.10.12-cp310-cp310-win_amd64.whl", hash = "sha256:e4129b528c6baa99a429f97ce733fff478ec955513630e61b49804b6cf9b224a"},
{file = "pydantic-1.10.12-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b0d191db0f92dfcb1dec210ca244fdae5cbe918c6050b342d619c09d31eea0cc"},
{file = "pydantic-1.10.12-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:795e34e6cc065f8f498c89b894a3c6da294a936ee71e644e4bd44de048af1405"},
{file = "pydantic-1.10.12-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:69328e15cfda2c392da4e713443c7dbffa1505bc9d566e71e55abe14c97ddc62"},
{file = "pydantic-1.10.12-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2031de0967c279df0d8a1c72b4ffc411ecd06bac607a212892757db7462fc494"},
{file = "pydantic-1.10.12-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:ba5b2e6fe6ca2b7e013398bc7d7b170e21cce322d266ffcd57cca313e54fb246"},
{file = "pydantic-1.10.12-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:2a7bac939fa326db1ab741c9d7f44c565a1d1e80908b3797f7f81a4f86bc8d33"},
{file = "pydantic-1.10.12-cp311-cp311-win_amd64.whl", hash = "sha256:87afda5539d5140cb8ba9e8b8c8865cb5b1463924d38490d73d3ccfd80896b3f"},
{file = "pydantic-1.10.12-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:549a8e3d81df0a85226963611950b12d2d334f214436a19537b2efed61b7639a"},
{file = "pydantic-1.10.12-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:598da88dfa127b666852bef6d0d796573a8cf5009ffd62104094a4fe39599565"},
{file = "pydantic-1.10.12-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ba5c4a8552bff16c61882db58544116d021d0b31ee7c66958d14cf386a5b5350"},
{file = "pydantic-1.10.12-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:c79e6a11a07da7374f46970410b41d5e266f7f38f6a17a9c4823db80dadf4303"},
{file = "pydantic-1.10.12-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:ab26038b8375581dc832a63c948f261ae0aa21f1d34c1293469f135fa92972a5"},
{file = "pydantic-1.10.12-cp37-cp37m-win_amd64.whl", hash = "sha256:e0a16d274b588767602b7646fa05af2782576a6cf1022f4ba74cbb4db66f6ca8"},
{file = "pydantic-1.10.12-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:6a9dfa722316f4acf4460afdf5d41d5246a80e249c7ff475c43a3a1e9d75cf62"},
{file = "pydantic-1.10.12-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:a73f489aebd0c2121ed974054cb2759af8a9f747de120acd2c3394cf84176ccb"},
{file = "pydantic-1.10.12-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b30bcb8cbfccfcf02acb8f1a261143fab622831d9c0989707e0e659f77a18e0"},
{file = "pydantic-1.10.12-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2fcfb5296d7877af406ba1547dfde9943b1256d8928732267e2653c26938cd9c"},
{file = "pydantic-1.10.12-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:2f9a6fab5f82ada41d56b0602606a5506aab165ca54e52bc4545028382ef1c5d"},
{file = "pydantic-1.10.12-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:dea7adcc33d5d105896401a1f37d56b47d443a2b2605ff8a969a0ed5543f7e33"},
{file = "pydantic-1.10.12-cp38-cp38-win_amd64.whl", hash = "sha256:1eb2085c13bce1612da8537b2d90f549c8cbb05c67e8f22854e201bde5d98a47"},
{file = "pydantic-1.10.12-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:ef6c96b2baa2100ec91a4b428f80d8f28a3c9e53568219b6c298c1125572ebc6"},
{file = "pydantic-1.10.12-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:6c076be61cd0177a8433c0adcb03475baf4ee91edf5a4e550161ad57fc90f523"},
{file = "pydantic-1.10.12-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2d5a58feb9a39f481eda4d5ca220aa8b9d4f21a41274760b9bc66bfd72595b86"},
{file = "pydantic-1.10.12-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e5f805d2d5d0a41633651a73fa4ecdd0b3d7a49de4ec3fadf062fe16501ddbf1"},
{file = "pydantic-1.10.12-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:1289c180abd4bd4555bb927c42ee42abc3aee02b0fb2d1223fb7c6e5bef87dbe"},
{file = "pydantic-1.10.12-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:5d1197e462e0364906cbc19681605cb7c036f2475c899b6f296104ad42b9f5fb"},
{file = "pydantic-1.10.12-cp39-cp39-win_amd64.whl", hash = "sha256:fdbdd1d630195689f325c9ef1a12900524dceb503b00a987663ff4f58669b93d"},
{file = "pydantic-1.10.12-py3-none-any.whl", hash = "sha256:b749a43aa51e32839c9d71dc67eb1e4221bb04af1033a32e3923d46f9effa942"},
{file = "pydantic-1.10.12.tar.gz", hash = "sha256:0fe8a415cea8f340e7a9af9c54fc71a649b43e8ca3cc732986116b3cb135d303"},
]
[package.dependencies]
typing-extensions = ">=4.2.0"
[package.extras]
dotenv = ["python-dotenv (>=0.10.4)"]
email = ["email-validator (>=1.0.3)"]
[[package]]
name = "pytest"
version = "7.4.0"
description = "pytest: simple powerful testing with Python"
optional = false
python-versions = ">=3.7"
files = [
{file = "pytest-7.4.0-py3-none-any.whl", hash = "sha256:78bf16451a2eb8c7a2ea98e32dc119fd2aa758f1d5d66dbf0a59d69a3969df32"},
{file = "pytest-7.4.0.tar.gz", hash = "sha256:b4bf8c45bd59934ed84001ad51e11b4ee40d40a1229d2c79f9c592b0a3f6bd8a"},
]
[package.dependencies]
colorama = {version = "*", markers = "sys_platform == \"win32\""}
exceptiongroup = {version = ">=1.0.0rc8", markers = "python_version < \"3.11\""}
iniconfig = "*"
packaging = "*"
pluggy = ">=0.12,<2.0"
tomli = {version = ">=1.0.0", markers = "python_version < \"3.11\""}
[package.extras]
testing = ["argcomplete", "attrs (>=19.2.0)", "hypothesis (>=3.56)", "mock", "nose", "pygments (>=2.7.2)", "requests", "setuptools", "xmlschema"]
[[package]]
name = "pytest-asyncio"
version = "0.21.1"
description = "Pytest support for asyncio"
optional = false
python-versions = ">=3.7"
files = [
{file = "pytest-asyncio-0.21.1.tar.gz", hash = "sha256:40a7eae6dded22c7b604986855ea48400ab15b069ae38116e8c01238e9eeb64d"},
{file = "pytest_asyncio-0.21.1-py3-none-any.whl", hash = "sha256:8666c1c8ac02631d7c51ba282e0c69a8a452b211ffedf2599099845da5c5c37b"},
]
[package.dependencies]
pytest = ">=7.0.0"
[package.extras]
docs = ["sphinx (>=5.3)", "sphinx-rtd-theme (>=1.0)"]
testing = ["coverage (>=6.2)", "flaky (>=3.5.0)", "hypothesis (>=5.7.1)", "mypy (>=0.931)", "pytest-trio (>=0.7.0)"]
[[package]]
name = "pywin32"
version = "306"
description = "Python for Window Extensions"
optional = false
python-versions = "*"
files = [
{file = "pywin32-306-cp310-cp310-win32.whl", hash = "sha256:06d3420a5155ba65f0b72f2699b5bacf3109f36acbe8923765c22938a69dfc8d"},
{file = "pywin32-306-cp310-cp310-win_amd64.whl", hash = "sha256:84f4471dbca1887ea3803d8848a1616429ac94a4a8d05f4bc9c5dcfd42ca99c8"},
{file = "pywin32-306-cp311-cp311-win32.whl", hash = "sha256:e65028133d15b64d2ed8f06dd9fbc268352478d4f9289e69c190ecd6818b6407"},
{file = "pywin32-306-cp311-cp311-win_amd64.whl", hash = "sha256:a7639f51c184c0272e93f244eb24dafca9b1855707d94c192d4a0b4c01e1100e"},
{file = "pywin32-306-cp311-cp311-win_arm64.whl", hash = "sha256:70dba0c913d19f942a2db25217d9a1b726c278f483a919f1abfed79c9cf64d3a"},
{file = "pywin32-306-cp312-cp312-win32.whl", hash = "sha256:383229d515657f4e3ed1343da8be101000562bf514591ff383ae940cad65458b"},
{file = "pywin32-306-cp312-cp312-win_amd64.whl", hash = "sha256:37257794c1ad39ee9be652da0462dc2e394c8159dfd913a8a4e8eb6fd346da0e"},
{file = "pywin32-306-cp312-cp312-win_arm64.whl", hash = "sha256:5821ec52f6d321aa59e2db7e0a35b997de60c201943557d108af9d4ae1ec7040"},
{file = "pywin32-306-cp37-cp37m-win32.whl", hash = "sha256:1c73ea9a0d2283d889001998059f5eaaba3b6238f767c9cf2833b13e6a685f65"},
{file = "pywin32-306-cp37-cp37m-win_amd64.whl", hash = "sha256:72c5f621542d7bdd4fdb716227be0dd3f8565c11b280be6315b06ace35487d36"},
{file = "pywin32-306-cp38-cp38-win32.whl", hash = "sha256:e4c092e2589b5cf0d365849e73e02c391c1349958c5ac3e9d5ccb9a28e017b3a"},
{file = "pywin32-306-cp38-cp38-win_amd64.whl", hash = "sha256:e8ac1ae3601bee6ca9f7cb4b5363bf1c0badb935ef243c4733ff9a393b1690c0"},
{file = "pywin32-306-cp39-cp39-win32.whl", hash = "sha256:e25fd5b485b55ac9c057f67d94bc203f3f6595078d1fb3b458c9c28b7153a802"},
{file = "pywin32-306-cp39-cp39-win_amd64.whl", hash = "sha256:39b61c15272833b5c329a2989999dcae836b1eed650252ab1b7bfbe1d59f30f4"},
]
[[package]]
name = "pyyaml"
version = "6.0.1"
description = "YAML parser and emitter for Python"
optional = false
python-versions = ">=3.6"
files = [
{file = "PyYAML-6.0.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:d858aa552c999bc8a8d57426ed01e40bef403cd8ccdd0fc5f6f04a00414cac2a"},
{file = "PyYAML-6.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:fd66fc5d0da6d9815ba2cebeb4205f95818ff4b79c3ebe268e75d961704af52f"},
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"},
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"},
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"},
{file = "PyYAML-6.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:326c013efe8048858a6d312ddd31d56e468118ad4cdeda36c719bf5bb6192290"},
{file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"},
{file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"},
{file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"},
{file = "PyYAML-6.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f003ed9ad21d6a4713f0a9b5a7a0a79e08dd0f221aff4525a2be4c346ee60aab"},
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"},
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"},
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"},
{file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"},
{file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"},
{file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
{file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
{file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
{file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
{file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
{file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
{file = "PyYAML-6.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:0d3304d8c0adc42be59c5f8a4d9e3d7379e6955ad754aa9d6ab7a398b59dd1df"},
{file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"},
{file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"},
{file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"},
{file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:afd7e57eddb1a54f0f1a974bc4391af8bcce0b444685d936840f125cf046d5bd"},
{file = "PyYAML-6.0.1-cp36-cp36m-win32.whl", hash = "sha256:fca0e3a251908a499833aa292323f32437106001d436eca0e6e7833256674585"},
{file = "PyYAML-6.0.1-cp36-cp36m-win_amd64.whl", hash = "sha256:f22ac1c3cac4dbc50079e965eba2c1058622631e526bd9afd45fedd49ba781fa"},
{file = "PyYAML-6.0.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:b1275ad35a5d18c62a7220633c913e1b42d44b46ee12554e5fd39c70a243d6a3"},
{file = "PyYAML-6.0.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:18aeb1bf9a78867dc38b259769503436b7c72f7a1f1f4c93ff9a17de54319b27"},
{file = "PyYAML-6.0.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:596106435fa6ad000c2991a98fa58eeb8656ef2325d7e158344fb33864ed87e3"},
{file = "PyYAML-6.0.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:baa90d3f661d43131ca170712d903e6295d1f7a0f595074f151c0aed377c9b9c"},
{file = "PyYAML-6.0.1-cp37-cp37m-win32.whl", hash = "sha256:9046c58c4395dff28dd494285c82ba00b546adfc7ef001486fbf0324bc174fba"},
{file = "PyYAML-6.0.1-cp37-cp37m-win_amd64.whl", hash = "sha256:4fb147e7a67ef577a588a0e2c17b6db51dda102c71de36f8549b6816a96e1867"},
{file = "PyYAML-6.0.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1d4c7e777c441b20e32f52bd377e0c409713e8bb1386e1099c2415f26e479595"},
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"},
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"},
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"},
{file = "PyYAML-6.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49a183be227561de579b4a36efbb21b3eab9651dd81b1858589f796549873dd6"},
{file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"},
{file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"},
{file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"},
{file = "PyYAML-6.0.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:c8098ddcc2a85b61647b2590f825f3db38891662cfc2fc776415143f599bb859"},
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"},
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"},
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"},
{file = "PyYAML-6.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:04ac92ad1925b2cff1db0cfebffb6ffc43457495c9b3c39d3fcae417d7125dc5"},
{file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"},
{file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"},
{file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"},
]
[[package]]
name = "requests"
version = "2.31.0"
description = "Python HTTP for Humans."
optional = false
python-versions = ">=3.7"
files = [
{file = "requests-2.31.0-py3-none-any.whl", hash = "sha256:58cd2187c01e70e6e26505bca751777aa9f2ee0b7f4300988b709f44e013003f"},
{file = "requests-2.31.0.tar.gz", hash = "sha256:942c5a758f98d790eaed1a29cb6eefc7ffb0d1cf7af05c3d2791656dbd6ad1e1"},
]
[package.dependencies]
certifi = ">=2017.4.17"
charset-normalizer = ">=2,<4"
idna = ">=2.5,<4"
urllib3 = ">=1.21.1,<3"
[package.extras]
socks = ["PySocks (>=1.5.6,!=1.5.7)"]
use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
[[package]]
name = "syrupy"
version = "4.0.1"
description = "Pytest Snapshot Test Utility"
optional = false
python-versions = ">=3.8.1,<4"
files = [
{file = "syrupy-4.0.1-py3-none-any.whl", hash = "sha256:53d3107cc5e18a5def189c721879cea2cdafdee34b879f602133ca08837d0e4b"},
{file = "syrupy-4.0.1.tar.gz", hash = "sha256:60e3e94782444e0f978cd3b207de32f6da3199b15a2db32eab02f83cebb63ae8"},
]
[package.dependencies]
colored = ">=1.3.92,<2.0.0"
pytest = ">=7.0.0,<8.0.0"
[[package]]
name = "text-generation"
version = "0.6.0"
description = "Hugging Face Text Generation Python Client"
optional = false
python-versions = ">=3.7,<4.0"
files = [
{file = "text-generation-0.6.0.tar.gz", hash = "sha256:48560e7a67b9a88b38335382d357f66e23b5a75f53971ccd436fc6f696a00815"},
{file = "text_generation-0.6.0-py3-none-any.whl", hash = "sha256:42ae7f7c9ff11f3a6c9d210f94fe708fe693eede79c6776da727456da1606ef9"},
]
[package.dependencies]
aiohttp = ">=3.8,<4.0"
huggingface-hub = ">=0.12,<1.0"
pydantic = ">=1.10,<2.0"
[[package]]
name = "tomli"
version = "2.0.1"
description = "A lil' TOML parser"
optional = false
python-versions = ">=3.7"
files = [
{file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
{file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
]
[[package]]
name = "tqdm"
version = "4.66.1"
description = "Fast, Extensible Progress Meter"
optional = false
python-versions = ">=3.7"
files = [
{file = "tqdm-4.66.1-py3-none-any.whl", hash = "sha256:d302b3c5b53d47bce91fea46679d9c3c6508cf6332229aa1e7d8653723793386"},
{file = "tqdm-4.66.1.tar.gz", hash = "sha256:d88e651f9db8d8551a62556d3cff9e3034274ca5d66e93197cf2490e2dcb69c7"},
]
[package.dependencies]
colorama = {version = "*", markers = "platform_system == \"Windows\""}
[package.extras]
dev = ["pytest (>=6)", "pytest-cov", "pytest-timeout", "pytest-xdist"]
notebook = ["ipywidgets (>=6)"]
slack = ["slack-sdk"]
telegram = ["requests"]
[[package]]
name = "typing-extensions"
version = "4.7.1"
description = "Backported and Experimental Type Hints for Python 3.7+"
optional = false
python-versions = ">=3.7"
files = [
{file = "typing_extensions-4.7.1-py3-none-any.whl", hash = "sha256:440d5dd3af93b060174bf433bccd69b0babc3b15b1a8dca43789fd7f61514b36"},
{file = "typing_extensions-4.7.1.tar.gz", hash = "sha256:b75ddc264f0ba5615db7ba217daeb99701ad295353c45f9e95963337ceeeffb2"},
]
[[package]]
name = "urllib3"
version = "2.0.4"
description = "HTTP library with thread-safe connection pooling, file post, and more."
optional = false
python-versions = ">=3.7"
files = [
{file = "urllib3-2.0.4-py3-none-any.whl", hash = "sha256:de7df1803967d2c2a98e4b11bb7d6bd9210474c46e8a0401514e3a42a75ebde4"},
{file = "urllib3-2.0.4.tar.gz", hash = "sha256:8d22f86aae8ef5e410d4f539fde9ce6b2113a001bb4d189e0aed70642d602b11"},
]
[package.extras]
brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)"]
secure = ["certifi", "cryptography (>=1.9)", "idna (>=2.0.0)", "pyopenssl (>=17.1.0)", "urllib3-secure-extra"]
socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
zstd = ["zstandard (>=0.18.0)"]
[[package]]
name = "websocket-client"
version = "1.6.2"
description = "WebSocket client for Python with low level API options"
optional = false
python-versions = ">=3.8"
files = [
{file = "websocket-client-1.6.2.tar.gz", hash = "sha256:53e95c826bf800c4c465f50093a8c4ff091c7327023b10bfaff40cf1ef170eaa"},
{file = "websocket_client-1.6.2-py3-none-any.whl", hash = "sha256:ce54f419dfae71f4bdba69ebe65bf7f0a93fe71bc009ad3a010aacc3eebad537"},
]
[package.extras]
docs = ["Sphinx (>=6.0)", "sphinx-rtd-theme (>=1.1.0)"]
optional = ["python-socks", "wsaccel"]
test = ["websockets"]
[[package]]
name = "yarl"
version = "1.9.2"
description = "Yet another URL library"
optional = false
python-versions = ">=3.7"
files = [
{file = "yarl-1.9.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:8c2ad583743d16ddbdf6bb14b5cd76bf43b0d0006e918809d5d4ddf7bde8dd82"},
{file = "yarl-1.9.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:82aa6264b36c50acfb2424ad5ca537a2060ab6de158a5bd2a72a032cc75b9eb8"},
{file = "yarl-1.9.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:c0c77533b5ed4bcc38e943178ccae29b9bcf48ffd1063f5821192f23a1bd27b9"},
{file = "yarl-1.9.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ee4afac41415d52d53a9833ebae7e32b344be72835bbb589018c9e938045a560"},
{file = "yarl-1.9.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9bf345c3a4f5ba7f766430f97f9cc1320786f19584acc7086491f45524a551ac"},
{file = "yarl-1.9.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2a96c19c52ff442a808c105901d0bdfd2e28575b3d5f82e2f5fd67e20dc5f4ea"},
{file = "yarl-1.9.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:891c0e3ec5ec881541f6c5113d8df0315ce5440e244a716b95f2525b7b9f3608"},
{file = "yarl-1.9.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c3a53ba34a636a256d767c086ceb111358876e1fb6b50dfc4d3f4951d40133d5"},
{file = "yarl-1.9.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:566185e8ebc0898b11f8026447eacd02e46226716229cea8db37496c8cdd26e0"},
{file = "yarl-1.9.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:2b0738fb871812722a0ac2154be1f049c6223b9f6f22eec352996b69775b36d4"},
{file = "yarl-1.9.2-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:32f1d071b3f362c80f1a7d322bfd7b2d11e33d2adf395cc1dd4df36c9c243095"},
{file = "yarl-1.9.2-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:e9fdc7ac0d42bc3ea78818557fab03af6181e076a2944f43c38684b4b6bed8e3"},
{file = "yarl-1.9.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:56ff08ab5df8429901ebdc5d15941b59f6253393cb5da07b4170beefcf1b2528"},
{file = "yarl-1.9.2-cp310-cp310-win32.whl", hash = "sha256:8ea48e0a2f931064469bdabca50c2f578b565fc446f302a79ba6cc0ee7f384d3"},
{file = "yarl-1.9.2-cp310-cp310-win_amd64.whl", hash = "sha256:50f33040f3836e912ed16d212f6cc1efb3231a8a60526a407aeb66c1c1956dde"},
{file = "yarl-1.9.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:646d663eb2232d7909e6601f1a9107e66f9791f290a1b3dc7057818fe44fc2b6"},
{file = "yarl-1.9.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:aff634b15beff8902d1f918012fc2a42e0dbae6f469fce134c8a0dc51ca423bb"},
{file = "yarl-1.9.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:a83503934c6273806aed765035716216cc9ab4e0364f7f066227e1aaea90b8d0"},
{file = "yarl-1.9.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b25322201585c69abc7b0e89e72790469f7dad90d26754717f3310bfe30331c2"},
{file = "yarl-1.9.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:22a94666751778629f1ec4280b08eb11815783c63f52092a5953faf73be24191"},
{file = "yarl-1.9.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8ec53a0ea2a80c5cd1ab397925f94bff59222aa3cf9c6da938ce05c9ec20428d"},
{file = "yarl-1.9.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:159d81f22d7a43e6eabc36d7194cb53f2f15f498dbbfa8edc8a3239350f59fe7"},
{file = "yarl-1.9.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:832b7e711027c114d79dffb92576acd1bd2decc467dec60e1cac96912602d0e6"},
{file = "yarl-1.9.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:95d2ecefbcf4e744ea952d073c6922e72ee650ffc79028eb1e320e732898d7e8"},
{file = "yarl-1.9.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:d4e2c6d555e77b37288eaf45b8f60f0737c9efa3452c6c44626a5455aeb250b9"},
{file = "yarl-1.9.2-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:783185c75c12a017cc345015ea359cc801c3b29a2966c2655cd12b233bf5a2be"},
{file = "yarl-1.9.2-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:b8cc1863402472f16c600e3e93d542b7e7542a540f95c30afd472e8e549fc3f7"},
{file = "yarl-1.9.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:822b30a0f22e588b32d3120f6d41e4ed021806418b4c9f0bc3048b8c8cb3f92a"},
{file = "yarl-1.9.2-cp311-cp311-win32.whl", hash = "sha256:a60347f234c2212a9f0361955007fcf4033a75bf600a33c88a0a8e91af77c0e8"},
{file = "yarl-1.9.2-cp311-cp311-win_amd64.whl", hash = "sha256:be6b3fdec5c62f2a67cb3f8c6dbf56bbf3f61c0f046f84645cd1ca73532ea051"},
{file = "yarl-1.9.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:38a3928ae37558bc1b559f67410df446d1fbfa87318b124bf5032c31e3447b74"},
{file = "yarl-1.9.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ac9bb4c5ce3975aeac288cfcb5061ce60e0d14d92209e780c93954076c7c4367"},
{file = "yarl-1.9.2-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3da8a678ca8b96c8606bbb8bfacd99a12ad5dd288bc6f7979baddd62f71c63ef"},
{file = "yarl-1.9.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:13414591ff516e04fcdee8dc051c13fd3db13b673c7a4cb1350e6b2ad9639ad3"},
{file = "yarl-1.9.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bf74d08542c3a9ea97bb8f343d4fcbd4d8f91bba5ec9d5d7f792dbe727f88938"},
{file = "yarl-1.9.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6e7221580dc1db478464cfeef9b03b95c5852cc22894e418562997df0d074ccc"},
{file = "yarl-1.9.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:494053246b119b041960ddcd20fd76224149cfea8ed8777b687358727911dd33"},
{file = "yarl-1.9.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:52a25809fcbecfc63ac9ba0c0fb586f90837f5425edfd1ec9f3372b119585e45"},
{file = "yarl-1.9.2-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:e65610c5792870d45d7b68c677681376fcf9cc1c289f23e8e8b39c1485384185"},
{file = "yarl-1.9.2-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:1b1bba902cba32cdec51fca038fd53f8beee88b77efc373968d1ed021024cc04"},
{file = "yarl-1.9.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:662e6016409828ee910f5d9602a2729a8a57d74b163c89a837de3fea050c7582"},
{file = "yarl-1.9.2-cp37-cp37m-win32.whl", hash = "sha256:f364d3480bffd3aa566e886587eaca7c8c04d74f6e8933f3f2c996b7f09bee1b"},
{file = "yarl-1.9.2-cp37-cp37m-win_amd64.whl", hash = "sha256:6a5883464143ab3ae9ba68daae8e7c5c95b969462bbe42e2464d60e7e2698368"},
{file = "yarl-1.9.2-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:5610f80cf43b6202e2c33ba3ec2ee0a2884f8f423c8f4f62906731d876ef4fac"},
{file = "yarl-1.9.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:b9a4e67ad7b646cd6f0938c7ebfd60e481b7410f574c560e455e938d2da8e0f4"},
{file = "yarl-1.9.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:83fcc480d7549ccebe9415d96d9263e2d4226798c37ebd18c930fce43dfb9574"},
{file = "yarl-1.9.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5fcd436ea16fee7d4207c045b1e340020e58a2597301cfbcfdbe5abd2356c2fb"},
{file = "yarl-1.9.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:84e0b1599334b1e1478db01b756e55937d4614f8654311eb26012091be109d59"},
{file = "yarl-1.9.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3458a24e4ea3fd8930e934c129b676c27452e4ebda80fbe47b56d8c6c7a63a9e"},
{file = "yarl-1.9.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:838162460b3a08987546e881a2bfa573960bb559dfa739e7800ceeec92e64417"},
{file = "yarl-1.9.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f4e2d08f07a3d7d3e12549052eb5ad3eab1c349c53ac51c209a0e5991bbada78"},
{file = "yarl-1.9.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:de119f56f3c5f0e2fb4dee508531a32b069a5f2c6e827b272d1e0ff5ac040333"},
{file = "yarl-1.9.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:149ddea5abf329752ea5051b61bd6c1d979e13fbf122d3a1f9f0c8be6cb6f63c"},
{file = "yarl-1.9.2-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:674ca19cbee4a82c9f54e0d1eee28116e63bc6fd1e96c43031d11cbab8b2afd5"},
{file = "yarl-1.9.2-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:9b3152f2f5677b997ae6c804b73da05a39daa6a9e85a512e0e6823d81cdad7cc"},
{file = "yarl-1.9.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:5415d5a4b080dc9612b1b63cba008db84e908b95848369aa1da3686ae27b6d2b"},
{file = "yarl-1.9.2-cp38-cp38-win32.whl", hash = "sha256:f7a3d8146575e08c29ed1cd287068e6d02f1c7bdff8970db96683b9591b86ee7"},
{file = "yarl-1.9.2-cp38-cp38-win_amd64.whl", hash = "sha256:63c48f6cef34e6319a74c727376e95626f84ea091f92c0250a98e53e62c77c72"},
{file = "yarl-1.9.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:75df5ef94c3fdc393c6b19d80e6ef1ecc9ae2f4263c09cacb178d871c02a5ba9"},
{file = "yarl-1.9.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:c027a6e96ef77d401d8d5a5c8d6bc478e8042f1e448272e8d9752cb0aff8b5c8"},
{file = "yarl-1.9.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:f3b078dbe227f79be488ffcfc7a9edb3409d018e0952cf13f15fd6512847f3f7"},
{file = "yarl-1.9.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:59723a029760079b7d991a401386390c4be5bfec1e7dd83e25a6a0881859e716"},
{file = "yarl-1.9.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b03917871bf859a81ccb180c9a2e6c1e04d2f6a51d953e6a5cdd70c93d4e5a2a"},
{file = "yarl-1.9.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c1012fa63eb6c032f3ce5d2171c267992ae0c00b9e164efe4d73db818465fac3"},
{file = "yarl-1.9.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a74dcbfe780e62f4b5a062714576f16c2f3493a0394e555ab141bf0d746bb955"},
{file = "yarl-1.9.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8c56986609b057b4839968ba901944af91b8e92f1725d1a2d77cbac6972b9ed1"},
{file = "yarl-1.9.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:2c315df3293cd521033533d242d15eab26583360b58f7ee5d9565f15fee1bef4"},
{file = "yarl-1.9.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:b7232f8dfbd225d57340e441d8caf8652a6acd06b389ea2d3222b8bc89cbfca6"},
{file = "yarl-1.9.2-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:53338749febd28935d55b41bf0bcc79d634881195a39f6b2f767870b72514caf"},
{file = "yarl-1.9.2-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:066c163aec9d3d073dc9ffe5dd3ad05069bcb03fcaab8d221290ba99f9f69ee3"},
{file = "yarl-1.9.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:8288d7cd28f8119b07dd49b7230d6b4562f9b61ee9a4ab02221060d21136be80"},
{file = "yarl-1.9.2-cp39-cp39-win32.whl", hash = "sha256:b124e2a6d223b65ba8768d5706d103280914d61f5cae3afbc50fc3dfcc016623"},
{file = "yarl-1.9.2-cp39-cp39-win_amd64.whl", hash = "sha256:61016e7d582bc46a5378ffdd02cd0314fb8ba52f40f9cf4d9a5e7dbef88dee18"},
{file = "yarl-1.9.2.tar.gz", hash = "sha256:04ab9d4b9f587c06d801c2abfe9317b77cdf996c65a90d5e84ecc45010823571"},
]
[package.dependencies]
idna = ">=2.0"
multidict = ">=4.0"
[metadata]
lock-version = "2.0"
python-versions = ">=3.9,<3.13"
content-hash = "bdad1d22d29138010cd6b11e1b92dc0630b35634422413a8456dc85a15bee05e"

13
integration-tests/pyproject.toml Normal file
View File

@ -0,0 +1,13 @@
[tool.poetry]
name = "text-generation-integration-tests"
version = "1.0.3"
description = "Text Generation Inference integration tests"
authors = ["Nicolas Patry <nicolas@huggingface.co>"]
[tool.poetry.dependencies]
python = ">=3.9,<3.13"
syrupy = "4.0.1"
text-generation = "^0.6.0"
pytest = "^7.4.0"
pytest-asyncio = "^0.21.1"
docker = "^6.1.3"

38
integration-tests/requirements.txt
View File

@ -1,5 +1,33 @@
syrupy aiohttp==3.8.5 ; python_version >= "3.9" and python_version < "3.13"
text-generation aiosignal==1.3.1 ; python_version >= "3.9" and python_version < "3.13"
pytest async-timeout==4.0.3 ; python_version >= "3.9" and python_version < "3.13"
pytest-asyncio==0.17.2 attrs==23.1.0 ; python_version >= "3.9" and python_version < "3.13"
docker certifi==2023.7.22 ; python_version >= "3.9" and python_version < "3.13"
charset-normalizer==3.2.0 ; python_version >= "3.9" and python_version < "3.13"
colorama==0.4.6 ; python_version >= "3.9" and python_version < "3.13" and (sys_platform == "win32" or platform_system == "Windows")
colored==1.4.4 ; python_version >= "3.9" and python_version < "3.13"
docker==6.1.3 ; python_version >= "3.9" and python_version < "3.13"
exceptiongroup==1.1.3 ; python_version >= "3.9" and python_version < "3.11"
filelock==3.12.3 ; python_version >= "3.9" and python_version < "3.13"
frozenlist==1.4.0 ; python_version >= "3.9" and python_version < "3.13"
fsspec==2023.6.0 ; python_version >= "3.9" and python_version < "3.13"
huggingface-hub==0.16.4 ; python_version >= "3.9" and python_version < "3.13"
idna==3.4 ; python_version >= "3.9" and python_version < "3.13"
iniconfig==2.0.0 ; python_version >= "3.9" and python_version < "3.13"
multidict==6.0.4 ; python_version >= "3.9" and python_version < "3.13"
packaging==23.1 ; python_version >= "3.9" and python_version < "3.13"
pluggy==1.3.0 ; python_version >= "3.9" and python_version < "3.13"
pydantic==1.10.12 ; python_version >= "3.9" and python_version < "3.13"
pytest-asyncio==0.21.1 ; python_version >= "3.9" and python_version < "3.13"
pytest==7.4.0 ; python_version >= "3.9" and python_version < "3.13"
pywin32==306 ; python_version >= "3.9" and python_version < "3.13" and sys_platform == "win32"
pyyaml==6.0.1 ; python_version >= "3.9" and python_version < "3.13"
requests==2.31.0 ; python_version >= "3.9" and python_version < "3.13"
syrupy==4.0.1 ; python_version >= "3.9" and python_version < "3.13"
text-generation==0.6.0 ; python_version >= "3.9" and python_version < "3.13"
tomli==2.0.1 ; python_version >= "3.9" and python_version < "3.11"
tqdm==4.66.1 ; python_version >= "3.9" and python_version < "3.13"
typing-extensions==4.7.1 ; python_version >= "3.9" and python_version < "3.13"
urllib3==2.0.4 ; python_version >= "3.9" and python_version < "3.13"
websocket-client==1.6.2 ; python_version >= "3.9" and python_version < "3.13"
yarl==1.9.2 ; python_version >= "3.9" and python_version < "3.13"

10
launcher/src/main.rs
View File

@ -159,6 +159,14 @@ struct Args {
#[clap(default_value = "4", long, env)] #[clap(default_value = "4", long, env)]
max_stop_sequences: usize, max_stop_sequences: usize,
/// This is the maximum allowed value for clients to set `top_n_tokens`.
/// `top_n_tokens is used to return information about the the `n` most likely
/// tokens at each generation step, instead of just the sampled token. This
/// information can be used for downstream tasks like for classification or
/// ranking.
#[clap(default_value = "5", long, env)]
max_top_n_tokens: u32,
/// This is the maximum allowed input length (expressed in number of tokens) /// This is the maximum allowed input length (expressed in number of tokens)
/// for users. The larger this value, the longer prompt users can send which /// for users. The larger this value, the longer prompt users can send which
/// can impact the overall memory required to handle the load. /// can impact the overall memory required to handle the load.
@ -929,6 +937,8 @@ fn spawn_webserver(
args.max_best_of.to_string(), args.max_best_of.to_string(),
"--max-stop-sequences".to_string(), "--max-stop-sequences".to_string(),
args.max_stop_sequences.to_string(), args.max_stop_sequences.to_string(),
"--max-top-n-tokens".to_string(),
args.max_top_n_tokens.to_string(),
"--max-input-length".to_string(), "--max-input-length".to_string(),
args.max_input_length.to_string(), args.max_input_length.to_string(),
"--max-total-tokens".to_string(), "--max-total-tokens".to_string(),

15
proto/generate.proto
View File

@ -91,6 +91,8 @@ message Request {
StoppingCriteriaParameters stopping_parameters = 5; StoppingCriteriaParameters stopping_parameters = 5;
/// Return prefill logprobs /// Return prefill logprobs
bool prefill_logprobs = 6; bool prefill_logprobs = 6;
/// Return most likely n tokens
uint32 top_n_tokens = 7;
} }
message Batch { message Batch {
@ -141,6 +143,17 @@ message PrefillTokens {
repeated string texts = 3; repeated string texts = 3;
} }
message TopTokens {
/// Top Token IDs
repeated uint32 ids = 1;
/// Top Logprobs
repeated float logprobs = 2;
/// Top Token Texts
repeated string texts = 3;
/// If the tokens are special
repeated bool is_special = 6;
}
message Generation { message Generation {
/// Request ID /// Request ID
uint64 request_id = 1; uint64 request_id = 1;
@ -156,6 +169,8 @@ message Generation {
bool token_is_special = 6; bool token_is_special = 6;
/// Complete generated text /// Complete generated text
optional GeneratedText generated_text = 7; optional GeneratedText generated_text = 7;
/// Top tokens
TopTokens top_tokens = 8;
} }
message FilterBatchRequest { message FilterBatchRequest {

1
router/client/src/client.rs
View File

@ -131,6 +131,7 @@ impl Client {
ignore_eos_token: false, ignore_eos_token: false,
}), }),
prefill_logprobs: true, prefill_logprobs: true,
top_n_tokens: 20,
}); });
n_tokens += max_input_length; n_tokens += max_input_length;
} }

1
router/src/health.rs
View File

@ -50,6 +50,7 @@ impl Health {
stop_sequences: vec![], stop_sequences: vec![],
ignore_eos_token: false, ignore_eos_token: false,
}), }),
top_n_tokens: 0,
}; };
let batch = Batch { let batch = Batch {
id: BATCH_ID, id: BATCH_ID,

45
router/src/infer.rs
View File

@ -138,12 +138,15 @@ impl Infer {
&self, &self,
request: GenerateRequest, request: GenerateRequest,
) -> Result<InferResponse, InferError> { ) -> Result<InferResponse, InferError> {
let use_top_tokens = request.parameters.top_n_tokens.is_some_and(|x| x > 0);
// Create stream and keep semaphore permit as long as generate lives // Create stream and keep semaphore permit as long as generate lives
let (_permit, mut stream) = self.generate_stream(request).await?; let (_permit, mut stream) = self.generate_stream(request).await?;
// Return values // Return values
let mut result_prefill = Vec::new(); let mut result_prefill = Vec::new();
let mut result_tokens = Vec::new(); let mut result_tokens = Vec::new();
let mut result_top_tokens = Vec::new();
let mut result_generated_text = None; let mut result_generated_text = None;
let mut result_start = None; let mut result_start = None;
let mut result_queued = None; let mut result_queued = None;
@ -164,7 +167,10 @@ impl Infer {
.collect(); .collect();
} }
// Push last token // Push last token
InferStreamResponse::Token(token) => result_tokens.push(token), InferStreamResponse::Intermediate { token, top_tokens } => {
result_tokens.push(token);
result_top_tokens.push(top_tokens);
}
// Final message // Final message
// Set return values // Set return values
InferStreamResponse::End { InferStreamResponse::End {
@ -172,8 +178,10 @@ impl Infer {
generated_text, generated_text,
start, start,
queued, queued,
top_tokens,
} => { } => {
result_tokens.push(token); result_tokens.push(token);
result_top_tokens.push(top_tokens);
result_generated_text = Some(generated_text); result_generated_text = Some(generated_text);
result_start = Some(start); result_start = Some(start);
result_queued = Some(queued) result_queued = Some(queued)
@ -191,6 +199,11 @@ impl Infer {
generated_text, generated_text,
queued, queued,
start, start,
top_tokens: if use_top_tokens {
result_top_tokens
} else {
Vec::new()
},
}) })
} else { } else {
let err = InferError::IncompleteGeneration; let err = InferError::IncompleteGeneration;
@ -520,6 +533,26 @@ fn send_responses(
special: generation.token_is_special, special: generation.token_is_special,
}; };
// generation.top_tokens
let mut top_tokens = Vec::new();
if let Some(top_tokens_) = generation.top_tokens {
top_tokens.extend(
top_tokens_
.ids
.into_iter()
.zip(top_tokens_.logprobs.into_iter())
.zip(top_tokens_.texts.into_iter())
.zip(top_tokens_.is_special.into_iter())
.map(|(((id, logprob), text), special)| Token {
id,
text,
logprob,
special,
}),
)
}
if let Some(generated_text) = generation.generated_text { if let Some(generated_text) = generation.generated_text {
// Generation has ended // Generation has ended
stopped = true; stopped = true;
@ -527,6 +560,7 @@ fn send_responses(
entry.response_tx.send_timeout( entry.response_tx.send_timeout(
Ok(InferStreamResponse::End { Ok(InferStreamResponse::End {
token, token,
top_tokens,
generated_text, generated_text,
queued: entry.queue_time, queued: entry.queue_time,
start: entry.batch_time.unwrap(), start: entry.batch_time.unwrap(),
@ -536,7 +570,7 @@ fn send_responses(
} else { } else {
// Send message // Send message
entry.response_tx.send_timeout( entry.response_tx.send_timeout(
Ok(InferStreamResponse::Token(token)), Ok(InferStreamResponse::Intermediate { token, top_tokens }),
Duration::from_millis(10), Duration::from_millis(10),
)?; )?;
} }
@ -566,10 +600,14 @@ pub(crate) enum InferStreamResponse {
// Optional first message // Optional first message
Prefill(PrefillTokens), Prefill(PrefillTokens),
// Intermediate messages // Intermediate messages
Token(Token), Intermediate {
token: Token,
top_tokens: Vec<Token>,
},
// Last message // Last message
End { End {
token: Token, token: Token,
top_tokens: Vec<Token>,
generated_text: GeneratedText, generated_text: GeneratedText,
start: Instant, start: Instant,
queued: Instant, queued: Instant,
@ -583,6 +621,7 @@ pub(crate) struct InferResponse {
pub(crate) generated_text: GeneratedText, pub(crate) generated_text: GeneratedText,
pub(crate) queued: Instant, pub(crate) queued: Instant,
pub(crate) start: Instant, pub(crate) start: Instant,
pub(crate) top_tokens: Vec<Vec<Token>>,
} }
#[derive(Debug, Error)] #[derive(Debug, Error)]

10
router/src/lib.rs
View File

@ -135,6 +135,9 @@ pub(crate) struct GenerateParameters {
example = "null" example = "null"
)] )]
pub seed: Option<u64>, pub seed: Option<u64>,
#[serde(default)]
#[schema(exclusive_minimum = 0, nullable = true, default = "null", example = 5)]
pub top_n_tokens: Option<u32>,
} }
fn default_max_new_tokens() -> u32 { fn default_max_new_tokens() -> u32 {
@ -158,6 +161,7 @@ fn default_parameters() -> GenerateParameters {
details: false, details: false,
decoder_input_details: false, decoder_input_details: false,
seed: None, seed: None,
top_n_tokens: None,
} }
} }
@ -235,6 +239,8 @@ pub(crate) struct BestOfSequence {
pub seed: Option<u64>, pub seed: Option<u64>,
pub prefill: Vec<PrefillToken>, pub prefill: Vec<PrefillToken>,
pub tokens: Vec<Token>, pub tokens: Vec<Token>,
#[serde(skip_serializing_if = "Vec::is_empty")]
pub top_tokens: Vec<Vec<Token>>,
} }
#[derive(Serialize, ToSchema)] #[derive(Serialize, ToSchema)]
@ -249,6 +255,8 @@ pub(crate) struct Details {
pub tokens: Vec<Token>, pub tokens: Vec<Token>,
#[serde(skip_serializing_if = "Option::is_none")] #[serde(skip_serializing_if = "Option::is_none")]
pub best_of_sequences: Option<Vec<BestOfSequence>>, pub best_of_sequences: Option<Vec<BestOfSequence>>,
#[serde(skip_serializing_if = "Vec::is_empty")]
pub top_tokens: Vec<Vec<Token>>,
} }
#[derive(Serialize, ToSchema)] #[derive(Serialize, ToSchema)]
@ -272,6 +280,8 @@ pub(crate) struct StreamDetails {
#[derive(Serialize, ToSchema)] #[derive(Serialize, ToSchema)]
pub(crate) struct StreamResponse { pub(crate) struct StreamResponse {
pub token: Token, pub token: Token,
#[serde(skip_serializing_if = "Vec::is_empty")]
pub top_tokens: Vec<Token>,
#[schema(nullable = true, default = "null", example = "test")] #[schema(nullable = true, default = "null", example = "test")]
pub generated_text: Option<String>, pub generated_text: Option<String>,
#[schema(nullable = true, default = "null")] #[schema(nullable = true, default = "null")]

4
router/src/main.rs
View File

@ -29,6 +29,8 @@ struct Args {
max_best_of: usize, max_best_of: usize,
#[clap(default_value = "4", long, env)] #[clap(default_value = "4", long, env)]
max_stop_sequences: usize, max_stop_sequences: usize,
#[clap(default_value = "5", long, env)]
max_top_n_tokens: u32,
#[clap(default_value = "1024", long, env)] #[clap(default_value = "1024", long, env)]
max_input_length: usize, max_input_length: usize,
#[clap(default_value = "2048", long, env)] #[clap(default_value = "2048", long, env)]
@ -75,6 +77,7 @@ fn main() -> Result<(), RouterError> {
max_concurrent_requests, max_concurrent_requests,
max_best_of, max_best_of,
max_stop_sequences, max_stop_sequences,
max_top_n_tokens,
max_input_length, max_input_length,
max_total_tokens, max_total_tokens,
waiting_served_ratio, waiting_served_ratio,
@ -259,6 +262,7 @@ fn main() -> Result<(), RouterError> {
max_concurrent_requests, max_concurrent_requests,
max_best_of, max_best_of,
max_stop_sequences, max_stop_sequences,
max_top_n_tokens,
max_input_length, max_input_length,
max_total_tokens, max_total_tokens,
waiting_served_ratio, waiting_served_ratio,

2
router/src/queue.rs
View File

@ -235,6 +235,7 @@ impl State {
truncate: entry.request.truncate, truncate: entry.request.truncate,
parameters: Some(entry.request.parameters.clone()), parameters: Some(entry.request.parameters.clone()),
stopping_parameters: Some(entry.request.stopping_parameters.clone()), stopping_parameters: Some(entry.request.stopping_parameters.clone()),
top_n_tokens: entry.request.top_n_tokens,
}); });
// Set batch_time // Set batch_time
entry.batch_time = Some(Instant::now()); entry.batch_time = Some(Instant::now());
@ -328,6 +329,7 @@ mod tests {
max_new_tokens: 1, max_new_tokens: 1,
stop_sequences: vec![], stop_sequences: vec![],
}, },
top_n_tokens: 0,
}, },
response_tx, response_tx,
span: info_span!("entry"), span: info_span!("entry"),

14
router/src/server.rs
View File

@ -158,7 +158,7 @@ async fn generate(
add_prompt = Some(req.inputs.clone()); add_prompt = Some(req.inputs.clone());
} }
let details = req.parameters.details || req.parameters.decoder_input_details; let details: bool = req.parameters.details || req.parameters.decoder_input_details;
// Inference // Inference
let (response, best_of_responses) = match req.parameters.best_of { let (response, best_of_responses) = match req.parameters.best_of {
@ -191,6 +191,7 @@ async fn generate(
generated_tokens: response.generated_text.generated_tokens, generated_tokens: response.generated_text.generated_tokens,
prefill: response.prefill, prefill: response.prefill,
tokens: response.tokens, tokens: response.tokens,
top_tokens: response.top_tokens,
seed: response.generated_text.seed, seed: response.generated_text.seed,
} }
}) })
@ -204,6 +205,7 @@ async fn generate(
tokens: response.tokens, tokens: response.tokens,
seed: response.generated_text.seed, seed: response.generated_text.seed,
best_of_sequences, best_of_sequences,
top_tokens: response.top_tokens,
}) })
} }
false => None, false => None,
@ -385,12 +387,16 @@ async fn generate_stream(
// Prefill is ignored // Prefill is ignored
InferStreamResponse::Prefill(_) => {} InferStreamResponse::Prefill(_) => {}
// Yield event for every new token // Yield event for every new token
InferStreamResponse::Token(token) => { InferStreamResponse::Intermediate{
token,
top_tokens,
} => {
tracing::debug!(parent: &span, "Token: {:?}", token); tracing::debug!(parent: &span, "Token: {:?}", token);
// StreamResponse // StreamResponse
let stream_token = StreamResponse { let stream_token = StreamResponse {
token, token,
top_tokens: top_tokens,
generated_text: None, generated_text: None,
details: None, details: None,
}; };
@ -403,6 +409,7 @@ async fn generate_stream(
generated_text, generated_text,
start, start,
queued, queued,
top_tokens,
} => { } => {
// Token details // Token details
let details = match details { let details = match details {
@ -451,6 +458,7 @@ async fn generate_stream(
let stream_token = StreamResponse { let stream_token = StreamResponse {
token, token,
top_tokens: top_tokens,
generated_text: Some(output_text), generated_text: Some(output_text),
details details
}; };
@ -509,6 +517,7 @@ pub async fn run(
max_concurrent_requests: usize, max_concurrent_requests: usize,
max_best_of: usize, max_best_of: usize,
max_stop_sequences: usize, max_stop_sequences: usize,
max_top_n_tokens: u32,
max_input_length: usize, max_input_length: usize,
max_total_tokens: usize, max_total_tokens: usize,
waiting_served_ratio: f32, waiting_served_ratio: f32,
@ -571,6 +580,7 @@ pub async fn run(
tokenizer, tokenizer,
max_best_of, max_best_of,
max_stop_sequences, max_stop_sequences,
max_top_n_tokens,
max_input_length, max_input_length,
max_total_tokens, max_total_tokens,
); );

116
router/src/validation.rs
View File

@ -15,6 +15,7 @@ pub struct Validation {
/// Validation parameters /// Validation parameters
max_best_of: usize, max_best_of: usize,
max_stop_sequences: usize, max_stop_sequences: usize,
max_top_n_tokens: u32,
max_input_length: usize, max_input_length: usize,
max_total_tokens: usize, max_total_tokens: usize,
/// Channel to communicate with the background tokenization task /// Channel to communicate with the background tokenization task
@ -27,6 +28,7 @@ impl Validation {
tokenizer: Option<Tokenizer>, tokenizer: Option<Tokenizer>,
max_best_of: usize, max_best_of: usize,
max_stop_sequences: usize, max_stop_sequences: usize,
max_top_n_tokens: u32,
max_input_length: usize, max_input_length: usize,
max_total_tokens: usize, max_total_tokens: usize,
) -> Self { ) -> Self {
@ -54,6 +56,7 @@ impl Validation {
max_best_of, max_best_of,
sender, sender,
max_stop_sequences, max_stop_sequences,
max_top_n_tokens,
max_input_length, max_input_length,
max_total_tokens, max_total_tokens,
} }
@ -142,6 +145,7 @@ impl Validation {
seed, seed,
watermark, watermark,
decoder_input_details, decoder_input_details,
top_n_tokens,
.. ..
} = request.parameters; } = request.parameters;
@ -218,6 +222,15 @@ impl Validation {
} }
}; };
let top_n_tokens = top_n_tokens
.map(|value| {
if value > self.max_top_n_tokens {
return Err(ValidationError::TopNTokens(self.max_top_n_tokens, value));
}
Ok(value)
})
.unwrap_or(Ok(0))?;
// Check if inputs is empty // Check if inputs is empty
if request.inputs.is_empty() { if request.inputs.is_empty() {
return Err(EmptyInput); return Err(EmptyInput);
@ -263,6 +276,7 @@ impl Validation {
truncate: truncate.unwrap_or(self.max_input_length) as u32, truncate: truncate.unwrap_or(self.max_input_length) as u32,
parameters, parameters,
stopping_parameters, stopping_parameters,
top_n_tokens: top_n_tokens,
}) })
} }
@ -336,6 +350,7 @@ pub(crate) struct ValidGenerateRequest {
pub decoder_input_details: bool, pub decoder_input_details: bool,
pub parameters: NextTokenChooserParameters, pub parameters: NextTokenChooserParameters,
pub stopping_parameters: StoppingCriteriaParameters, pub stopping_parameters: StoppingCriteriaParameters,
pub top_n_tokens: u32,
} }
#[derive(Error, Debug)] #[derive(Error, Debug)]
@ -350,6 +365,10 @@ pub enum ValidationError {
BestOfSeed, BestOfSeed,
#[error("`best_of` != 1 is not supported when streaming tokens")] #[error("`best_of` != 1 is not supported when streaming tokens")]
BestOfStream, BestOfStream,
#[error("`top_n_tokens` must be >= 0 and <= {0}. Given: {1}")]
TopNTokens(u32, u32),
#[error("`top_n_tokens` != 0 is not allowed for this endpoint")]
TopNTokensDisabled,
#[error("`decoder_input_details` == true is not supported when streaming tokens")] #[error("`decoder_input_details` == true is not supported when streaming tokens")]
PrefillDetailsStream, PrefillDetailsStream,
#[error("`temperature` must be strictly positive")] #[error("`temperature` must be strictly positive")]
@ -391,14 +410,16 @@ mod tests {
let tokenizer = None; let tokenizer = None;
let max_best_of = 2; let max_best_of = 2;
let max_stop_sequence = 3; let max_stop_sequence = 3;
let max_input_length = 4; let max_top_n_tokens = 4;
let max_total_tokens = 5; let max_input_length = 5;
let max_total_tokens = 6;
let workers = 1; let workers = 1;
let validation = Validation::new( let validation = Validation::new(
workers, workers,
tokenizer, tokenizer,
max_best_of, max_best_of,
max_stop_sequence, max_stop_sequence,
max_top_n_tokens,
max_input_length, max_input_length,
max_total_tokens, max_total_tokens,
); );
@ -418,14 +439,16 @@ mod tests {
let tokenizer = Some(get_tokenizer().await); let tokenizer = Some(get_tokenizer().await);
let max_best_of = 2; let max_best_of = 2;
let max_stop_sequence = 3; let max_stop_sequence = 3;
let max_input_length = 4; let max_top_n_tokens = 4;
let max_total_tokens = 5; let max_input_length = 5;
let max_total_tokens = 6;
let workers = 1; let workers = 1;
let validation = Validation::new( let validation = Validation::new(
workers, workers,
tokenizer, tokenizer,
max_best_of, max_best_of,
max_stop_sequence, max_stop_sequence,
max_top_n_tokens,
max_input_length, max_input_length,
max_total_tokens, max_total_tokens,
); );
@ -435,7 +458,7 @@ mod tests {
.validate_input("Hello".to_string(), None, max_new_tokens) .validate_input("Hello".to_string(), None, max_new_tokens)
.await .await
{ {
Err(ValidationError::MaxTotalTokens(5, 1, 10)) => (), Err(ValidationError::MaxTotalTokens(6, 1, 10)) => (),
_ => panic!("Unexpected not max new tokens"), _ => panic!("Unexpected not max new tokens"),
} }
} }
@ -445,14 +468,16 @@ mod tests {
let tokenizer = Some(get_tokenizer().await); let tokenizer = Some(get_tokenizer().await);
let max_best_of = 2; let max_best_of = 2;
let max_stop_sequence = 3; let max_stop_sequence = 3;
let max_input_length = 4; let max_top_n_tokens = 4;
let max_total_tokens = 5; let max_input_length = 5;
let max_total_tokens = 6;
let workers = 1; let workers = 1;
let validation = Validation::new( let validation = Validation::new(
workers, workers,
tokenizer, tokenizer,
max_best_of, max_best_of,
max_stop_sequence, max_stop_sequence,
max_top_n_tokens,
max_input_length, max_input_length,
max_total_tokens, max_total_tokens,
); );
@ -477,14 +502,16 @@ mod tests {
let tokenizer = Some(get_tokenizer().await); let tokenizer = Some(get_tokenizer().await);
let max_best_of = 2; let max_best_of = 2;
let max_stop_sequence = 3; let max_stop_sequence = 3;
let max_input_length = 4; let max_top_n_tokens = 4;
let max_total_tokens = 5; let max_input_length = 5;
let max_total_tokens = 6;
let workers = 1; let workers = 1;
let validation = Validation::new( let validation = Validation::new(
workers, workers,
tokenizer, tokenizer,
max_best_of, max_best_of,
max_stop_sequence, max_stop_sequence,
max_top_n_tokens,
max_input_length, max_input_length,
max_total_tokens, max_total_tokens,
); );
@ -531,4 +558,75 @@ mod tests {
// top_p == 1.0 is invalid for users to ask for but it's the default resolved value. // top_p == 1.0 is invalid for users to ask for but it's the default resolved value.
assert_eq!(valid_request.parameters.top_p, 1.0); assert_eq!(valid_request.parameters.top_p, 1.0);
} }
#[tokio::test]
async fn test_validation_top_n_tokens() {
let tokenizer = Some(get_tokenizer().await);
let max_best_of = 2;
let max_stop_sequences = 3;
let max_top_n_tokens = 4;
let max_input_length = 5;
let max_total_tokens = 6;
let workers = 1;
let validation = Validation::new(
workers,
tokenizer,
max_best_of,
max_stop_sequences,
max_top_n_tokens,
max_input_length,
max_total_tokens,
);
match validation
.validate(GenerateRequest {
inputs: "Hello".to_string(),
parameters: GenerateParameters {
top_n_tokens: Some(5),
..default_parameters()
},
})
.await
{
Err(ValidationError::TopNTokens(4, 5)) => (),
_ => panic!("Unexpected top_n_tokens"),
}
validation
.validate(GenerateRequest {
inputs: "Hello".to_string(),
parameters: GenerateParameters {
top_n_tokens: Some(4),
max_new_tokens: 1,
..default_parameters()
},
})
.await
.unwrap();
validation
.validate(GenerateRequest {
inputs: "Hello".to_string(),
parameters: GenerateParameters {
top_n_tokens: Some(0),
max_new_tokens: 1,
..default_parameters()
},
})
.await
.unwrap();
let valid_request = validation
.validate(GenerateRequest {
inputs: "Hello".to_string(),
parameters: GenerateParameters {
top_n_tokens: None,
max_new_tokens: 1,
..default_parameters()
},
})
.await
.unwrap();
assert_eq!(valid_request.top_n_tokens, 0);
}
} }

2
server/Makefile-vllm
View File

@ -1,4 +1,4 @@
vllm_commit := d284b831c17f42a8ea63369a06138325f73c4cf9 vllm_commit := e86af624d059969b0fb07b075b1d338bf10c3365
vllm: vllm:
# Clone vllm # Clone vllm

334
server/poetry.lock generated
View File

@ -298,13 +298,13 @@ files = [
[[package]] [[package]]
name = "click" name = "click"
version = "8.1.6" version = "8.1.7"
description = "Composable command line interface toolkit" description = "Composable command line interface toolkit"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "click-8.1.6-py3-none-any.whl", hash = "sha256:fa244bb30b3b5ee2cae3da8f55c9e5e0c0e86093306301fb418eb9dc40fbded5"}, {file = "click-8.1.7-py3-none-any.whl", hash = "sha256:ae74fb96c20a0277a1d615f1e4d73c8414f5a98db8b799a7931d1582f3390c28"},
{file = "click-8.1.6.tar.gz", hash = "sha256:48ee849951919527a045bfe3bf7baa8a959c423134e1a5b98c05c20ba75a1cbd"}, {file = "click-8.1.7.tar.gz", hash = "sha256:ca9853ad459e787e2192211578cc907e7594e294c7ccc834310722b41b9ca6de"},
] ]
[package.dependencies] [package.dependencies]
@ -421,18 +421,21 @@ test = ["pytest (>=6)"]
[[package]] [[package]]
name = "filelock" name = "filelock"
version = "3.12.2" version = "3.12.3"
description = "A platform independent file lock." description = "A platform independent file lock."
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.8"
files = [ files = [
{file = "filelock-3.12.2-py3-none-any.whl", hash = "sha256:cbb791cdea2a72f23da6ac5b5269ab0a0d161e9ef0100e653b69049a7706d1ec"}, {file = "filelock-3.12.3-py3-none-any.whl", hash = "sha256:f067e40ccc40f2b48395a80fcbd4728262fab54e232e090a4063ab804179efeb"},
{file = "filelock-3.12.2.tar.gz", hash = "sha256:002740518d8aa59a26b0c76e10fb8c6e15eae825d34b6fdf670333fd7b938d81"}, {file = "filelock-3.12.3.tar.gz", hash = "sha256:0ecc1dd2ec4672a10c8550a8182f1bd0c0a5088470ecd5a125e45f49472fac3d"},
] ]
[package.dependencies]
typing-extensions = {version = ">=4.7.1", markers = "python_version < \"3.11\""}
[package.extras] [package.extras]
docs = ["furo (>=2023.5.20)", "sphinx (>=7.0.1)", "sphinx-autodoc-typehints (>=1.23,!=1.23.4)"] docs = ["furo (>=2023.7.26)", "sphinx (>=7.1.2)", "sphinx-autodoc-typehints (>=1.24)"]
testing = ["covdefaults (>=2.3)", "coverage (>=7.2.7)", "diff-cover (>=7.5)", "pytest (>=7.3.1)", "pytest-cov (>=4.1)", "pytest-mock (>=3.10)", "pytest-timeout (>=2.1)"] testing = ["covdefaults (>=2.3)", "coverage (>=7.3)", "diff-cover (>=7.7)", "pytest (>=7.4)", "pytest-cov (>=4.1)", "pytest-mock (>=3.11.1)", "pytest-timeout (>=2.1)"]
[[package]] [[package]]
name = "frozenlist" name = "frozenlist"
@ -562,13 +565,13 @@ grpc = ["grpcio (>=1.44.0,<2.0.0.dev0)"]
[[package]] [[package]]
name = "grpc-interceptor" name = "grpc-interceptor"
version = "0.15.2" version = "0.15.3"
description = "Simplifies gRPC interceptors" description = "Simplifies gRPC interceptors"
optional = false optional = false
python-versions = ">=3.7,<4.0" python-versions = ">=3.7,<4.0"
files = [ files = [
{file = "grpc-interceptor-0.15.2.tar.gz", hash = "sha256:5c984110af4fb77d03472ec0468f9c77ddaf798e190410fb7b7f1e76c60c96a4"}, {file = "grpc-interceptor-0.15.3.tar.gz", hash = "sha256:33592cb9d8c00fceed5755c71029f75aef55b273496dbced06f1d48f2571fcc3"},
{file = "grpc_interceptor-0.15.2-py3-none-any.whl", hash = "sha256:596dac3cb709ffb6178a4873f5148e254c871c9069f0b11040189b257969490a"}, {file = "grpc_interceptor-0.15.3-py3-none-any.whl", hash = "sha256:96be2043b7e49f9deb444f18b61c373ea28d22d81c90cd3b82127a4744eb9247"},
] ]
[package.dependencies] [package.dependencies]
@ -754,13 +757,13 @@ files = [
[[package]] [[package]]
name = "huggingface-hub" name = "huggingface-hub"
version = "0.14.1" version = "0.16.4"
description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub" description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
optional = false optional = false
python-versions = ">=3.7.0" python-versions = ">=3.7.0"
files = [ files = [
{file = "huggingface_hub-0.14.1-py3-none-any.whl", hash = "sha256:9fc619170d800ff3793ad37c9757c255c8783051e1b5b00501205eb43ccc4f27"}, {file = "huggingface_hub-0.16.4-py3-none-any.whl", hash = "sha256:0d3df29932f334fead024afc7cb4cc5149d955238b8b5e42dcf9740d6995a349"},
{file = "huggingface_hub-0.14.1.tar.gz", hash = "sha256:9ab899af8e10922eac65e290d60ab956882ab0bf643e3d990b1394b6b47b7fbc"}, {file = "huggingface_hub-0.16.4.tar.gz", hash = "sha256:608c7d4f3d368b326d1747f91523dbd1f692871e8e2e7a4750314a2dd8b63e14"},
] ]
[package.dependencies] [package.dependencies]
@ -773,15 +776,16 @@ tqdm = ">=4.42.1"
typing-extensions = ">=3.7.4.3" typing-extensions = ">=3.7.4.3"
[package.extras] [package.extras]
all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "black (>=23.1,<24.0)", "gradio", "jedi", "mypy (==0.982)", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "ruff (>=0.0.241)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"] all = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "black (>=23.1,<24.0)", "gradio", "jedi", "mypy (==0.982)", "numpy", "pydantic", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-vcr", "pytest-xdist", "ruff (>=0.0.241)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "urllib3 (<2.0)"]
cli = ["InquirerPy (==0.3.4)"] cli = ["InquirerPy (==0.3.4)"]
dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "black (>=23.1,<24.0)", "gradio", "jedi", "mypy (==0.982)", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "ruff (>=0.0.241)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"] dev = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "black (>=23.1,<24.0)", "gradio", "jedi", "mypy (==0.982)", "numpy", "pydantic", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-vcr", "pytest-xdist", "ruff (>=0.0.241)", "soundfile", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "urllib3 (<2.0)"]
fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"] fastai = ["fastai (>=2.4)", "fastcore (>=1.3.27)", "toml"]
inference = ["aiohttp", "pydantic"]
quality = ["black (>=23.1,<24.0)", "mypy (==0.982)", "ruff (>=0.0.241)"] quality = ["black (>=23.1,<24.0)", "mypy (==0.982)", "ruff (>=0.0.241)"]
tensorflow = ["graphviz", "pydot", "tensorflow"] tensorflow = ["graphviz", "pydot", "tensorflow"]
testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "gradio", "jedi", "pytest", "pytest-cov", "pytest-env", "pytest-xdist", "soundfile"] testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "gradio", "jedi", "numpy", "pydantic", "pytest", "pytest-asyncio", "pytest-cov", "pytest-env", "pytest-vcr", "pytest-xdist", "soundfile", "urllib3 (<2.0)"]
torch = ["torch"] torch = ["torch"]
typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"] typing = ["pydantic", "types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3"]
[[package]] [[package]]
name = "idna" name = "idna"
@ -1409,13 +1413,13 @@ tests = ["check-manifest", "coverage", "defusedxml", "markdown2", "olefile", "pa
[[package]] [[package]]
name = "pluggy" name = "pluggy"
version = "1.2.0" version = "1.3.0"
description = "plugin and hook calling mechanisms for python" description = "plugin and hook calling mechanisms for python"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.8"
files = [ files = [
{file = "pluggy-1.2.0-py3-none-any.whl", hash = "sha256:c2fd55a7d7a3863cba1a013e4e2414658b1d07b6bc57b3919e0c63c9abb99849"}, {file = "pluggy-1.3.0-py3-none-any.whl", hash = "sha256:d89c696a773f8bd377d18e5ecda92b7a3793cbe66c87060a6fb58c7b6e1061f7"},
{file = "pluggy-1.2.0.tar.gz", hash = "sha256:d12f0c4b579b15f5e054301bb226ee85eeeba08ffec228092f8defbaa3a4c4b3"}, {file = "pluggy-1.3.0.tar.gz", hash = "sha256:cf61ae8f126ac6f7c451172cf30e3e43d3ca77615509771b3a984a0730651e12"},
] ]
[package.extras] [package.extras]
@ -1424,24 +1428,24 @@ testing = ["pytest", "pytest-benchmark"]
[[package]] [[package]]
name = "protobuf" name = "protobuf"
version = "4.24.0" version = "4.24.2"
description = "" description = ""
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.7"
files = [ files = [
{file = "protobuf-4.24.0-cp310-abi3-win32.whl", hash = "sha256:81cb9c4621d2abfe181154354f63af1c41b00a4882fb230b4425cbaed65e8f52"}, {file = "protobuf-4.24.2-cp310-abi3-win32.whl", hash = "sha256:58e12d2c1aa428ece2281cef09bbaa6938b083bcda606db3da4e02e991a0d924"},
{file = "protobuf-4.24.0-cp310-abi3-win_amd64.whl", hash = "sha256:6c817cf4a26334625a1904b38523d1b343ff8b637d75d2c8790189a4064e51c3"}, {file = "protobuf-4.24.2-cp310-abi3-win_amd64.whl", hash = "sha256:77700b55ba41144fc64828e02afb41901b42497b8217b558e4a001f18a85f2e3"},
{file = "protobuf-4.24.0-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:ae97b5de10f25b7a443b40427033e545a32b0e9dda17bcd8330d70033379b3e5"}, {file = "protobuf-4.24.2-cp37-abi3-macosx_10_9_universal2.whl", hash = "sha256:237b9a50bd3b7307d0d834c1b0eb1a6cd47d3f4c2da840802cd03ea288ae8880"},
{file = "protobuf-4.24.0-cp37-abi3-manylinux2014_aarch64.whl", hash = "sha256:567fe6b0647494845d0849e3d5b260bfdd75692bf452cdc9cb660d12457c055d"}, {file = "protobuf-4.24.2-cp37-abi3-manylinux2014_aarch64.whl", hash = "sha256:25ae91d21e3ce8d874211110c2f7edd6384816fb44e06b2867afe35139e1fd1c"},
{file = "protobuf-4.24.0-cp37-abi3-manylinux2014_x86_64.whl", hash = "sha256:a6b1ca92ccabfd9903c0c7dde8876221dc7d8d87ad5c42e095cc11b15d3569c7"}, {file = "protobuf-4.24.2-cp37-abi3-manylinux2014_x86_64.whl", hash = "sha256:c00c3c7eb9ad3833806e21e86dca448f46035242a680f81c3fe068ff65e79c74"},
{file = "protobuf-4.24.0-cp37-cp37m-win32.whl", hash = "sha256:a38400a692fd0c6944c3c58837d112f135eb1ed6cdad5ca6c5763336e74f1a04"}, {file = "protobuf-4.24.2-cp37-cp37m-win32.whl", hash = "sha256:4e69965e7e54de4db989289a9b971a099e626f6167a9351e9d112221fc691bc1"},
{file = "protobuf-4.24.0-cp37-cp37m-win_amd64.whl", hash = "sha256:5ab19ee50037d4b663c02218a811a5e1e7bb30940c79aac385b96e7a4f9daa61"}, {file = "protobuf-4.24.2-cp37-cp37m-win_amd64.whl", hash = "sha256:c5cdd486af081bf752225b26809d2d0a85e575b80a84cde5172a05bbb1990099"},
{file = "protobuf-4.24.0-cp38-cp38-win32.whl", hash = "sha256:e8834ef0b4c88666ebb7c7ec18045aa0f4325481d724daa624a4cf9f28134653"}, {file = "protobuf-4.24.2-cp38-cp38-win32.whl", hash = "sha256:6bd26c1fa9038b26c5c044ee77e0ecb18463e957fefbaeb81a3feb419313a54e"},
{file = "protobuf-4.24.0-cp38-cp38-win_amd64.whl", hash = "sha256:8bb52a2be32db82ddc623aefcedfe1e0eb51da60e18fcc908fb8885c81d72109"}, {file = "protobuf-4.24.2-cp38-cp38-win_amd64.whl", hash = "sha256:bb7aa97c252279da65584af0456f802bd4b2de429eb945bbc9b3d61a42a8cd16"},
{file = "protobuf-4.24.0-cp39-cp39-win32.whl", hash = "sha256:ae7a1835721086013de193311df858bc12cd247abe4ef9710b715d930b95b33e"}, {file = "protobuf-4.24.2-cp39-cp39-win32.whl", hash = "sha256:2b23bd6e06445699b12f525f3e92a916f2dcf45ffba441026357dea7fa46f42b"},
{file = "protobuf-4.24.0-cp39-cp39-win_amd64.whl", hash = "sha256:44825e963008f8ea0d26c51911c30d3e82e122997c3c4568fd0385dd7bacaedf"}, {file = "protobuf-4.24.2-cp39-cp39-win_amd64.whl", hash = "sha256:839952e759fc40b5d46be319a265cf94920174d88de31657d5622b5d8d6be5cd"},
{file = "protobuf-4.24.0-py3-none-any.whl", hash = "sha256:82e6e9ebdd15b8200e8423676eab38b774624d6a1ad696a60d86a2ac93f18201"}, {file = "protobuf-4.24.2-py3-none-any.whl", hash = "sha256:3b7b170d3491ceed33f723bbf2d5a260f8a4e23843799a3906f16ef736ef251e"},
{file = "protobuf-4.24.0.tar.gz", hash = "sha256:5d0ceb9de6e08311832169e601d1fc71bd8e8c779f3ee38a97a78554945ecb85"}, {file = "protobuf-4.24.2.tar.gz", hash = "sha256:7fda70797ddec31ddfa3576cbdcc3ddbb6b3078b737a1a87ab9136af0570cd6e"},
] ]
[[package]] [[package]]
@ -1472,36 +1476,40 @@ test = ["enum34", "ipaddress", "mock", "pywin32", "wmi"]
[[package]] [[package]]
name = "pyarrow" name = "pyarrow"
version = "12.0.1" version = "13.0.0"
description = "Python library for Apache Arrow" description = "Python library for Apache Arrow"
optional = true optional = true
python-versions = ">=3.7" python-versions = ">=3.8"
files = [ files = [
{file = "pyarrow-12.0.1-cp310-cp310-macosx_10_14_x86_64.whl", hash = "sha256:6d288029a94a9bb5407ceebdd7110ba398a00412c5b0155ee9813a40d246c5df"}, {file = "pyarrow-13.0.0-cp310-cp310-macosx_10_14_x86_64.whl", hash = "sha256:1afcc2c33f31f6fb25c92d50a86b7a9f076d38acbcb6f9e74349636109550148"},
{file = "pyarrow-12.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:345e1828efdbd9aa4d4de7d5676778aba384a2c3add896d995b23d368e60e5af"}, {file = "pyarrow-13.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:70fa38cdc66b2fc1349a082987f2b499d51d072faaa6b600f71931150de2e0e3"},
{file = "pyarrow-12.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8d6009fdf8986332b2169314da482baed47ac053311c8934ac6651e614deacd6"}, {file = "pyarrow-13.0.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cd57b13a6466822498238877892a9b287b0a58c2e81e4bdb0b596dbb151cbb73"},
{file = "pyarrow-12.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2d3c4cbbf81e6dd23fe921bc91dc4619ea3b79bc58ef10bce0f49bdafb103daf"}, {file = "pyarrow-13.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f8ce69f7bf01de2e2764e14df45b8404fc6f1a5ed9871e8e08a12169f87b7a26"},
{file = "pyarrow-12.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:cdacf515ec276709ac8042c7d9bd5be83b4f5f39c6c037a17a60d7ebfd92c890"}, {file = "pyarrow-13.0.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:588f0d2da6cf1b1680974d63be09a6530fd1bd825dc87f76e162404779a157dc"},
{file = "pyarrow-12.0.1-cp311-cp311-macosx_10_14_x86_64.whl", hash = "sha256:749be7fd2ff260683f9cc739cb862fb11be376de965a2a8ccbf2693b098db6c7"}, {file = "pyarrow-13.0.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:6241afd72b628787b4abea39e238e3ff9f34165273fad306c7acf780dd850956"},
{file = "pyarrow-12.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:6895b5fb74289d055c43db3af0de6e16b07586c45763cb5e558d38b86a91e3a7"}, {file = "pyarrow-13.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:fda7857e35993673fcda603c07d43889fca60a5b254052a462653f8656c64f44"},
{file = "pyarrow-12.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1887bdae17ec3b4c046fcf19951e71b6a619f39fa674f9881216173566c8f718"}, {file = "pyarrow-13.0.0-cp311-cp311-macosx_10_14_x86_64.whl", hash = "sha256:aac0ae0146a9bfa5e12d87dda89d9ef7c57a96210b899459fc2f785303dcbb67"},
{file = "pyarrow-12.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e2c9cb8eeabbadf5fcfc3d1ddea616c7ce893db2ce4dcef0ac13b099ad7ca082"}, {file = "pyarrow-13.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d7759994217c86c161c6a8060509cfdf782b952163569606bb373828afdd82e8"},
{file = "pyarrow-12.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:ce4aebdf412bd0eeb800d8e47db854f9f9f7e2f5a0220440acf219ddfddd4f63"}, {file = "pyarrow-13.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:868a073fd0ff6468ae7d869b5fc1f54de5c4255b37f44fb890385eb68b68f95d"},
{file = "pyarrow-12.0.1-cp37-cp37m-macosx_10_14_x86_64.whl", hash = "sha256:e0d8730c7f6e893f6db5d5b86eda42c0a130842d101992b581e2138e4d5663d3"}, {file = "pyarrow-13.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:51be67e29f3cfcde263a113c28e96aa04362ed8229cb7c6e5f5c719003659d33"},
{file = "pyarrow-12.0.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:43364daec02f69fec89d2315f7fbfbeec956e0d991cbbef471681bd77875c40f"}, {file = "pyarrow-13.0.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:d1b4e7176443d12610874bb84d0060bf080f000ea9ed7c84b2801df851320295"},
{file = "pyarrow-12.0.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:051f9f5ccf585f12d7de836e50965b3c235542cc896959320d9776ab93f3b33d"}, {file = "pyarrow-13.0.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:69b6f9a089d116a82c3ed819eea8fe67dae6105f0d81eaf0fdd5e60d0c6e0944"},
{file = "pyarrow-12.0.1-cp37-cp37m-win_amd64.whl", hash = "sha256:be2757e9275875d2a9c6e6052ac7957fbbfc7bc7370e4a036a9b893e96fedaba"}, {file = "pyarrow-13.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:ab1268db81aeb241200e321e220e7cd769762f386f92f61b898352dd27e402ce"},
{file = "pyarrow-12.0.1-cp38-cp38-macosx_10_14_x86_64.whl", hash = "sha256:cf812306d66f40f69e684300f7af5111c11f6e0d89d6b733e05a3de44961529d"}, {file = "pyarrow-13.0.0-cp38-cp38-macosx_10_14_x86_64.whl", hash = "sha256:ee7490f0f3f16a6c38f8c680949551053c8194e68de5046e6c288e396dccee80"},
{file = "pyarrow-12.0.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:459a1c0ed2d68671188b2118c63bac91eaef6fc150c77ddd8a583e3c795737bf"}, {file = "pyarrow-13.0.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:e3ad79455c197a36eefbd90ad4aa832bece7f830a64396c15c61a0985e337287"},
{file = "pyarrow-12.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:85e705e33eaf666bbe508a16fd5ba27ca061e177916b7a317ba5a51bee43384c"}, {file = "pyarrow-13.0.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:68fcd2dc1b7d9310b29a15949cdd0cb9bc34b6de767aff979ebf546020bf0ba0"},
{file = "pyarrow-12.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9120c3eb2b1f6f516a3b7a9714ed860882d9ef98c4b17edcdc91d95b7528db60"}, {file = "pyarrow-13.0.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dc6fd330fd574c51d10638e63c0d00ab456498fc804c9d01f2a61b9264f2c5b2"},
{file = "pyarrow-12.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:c780f4dc40460015d80fcd6a6140de80b615349ed68ef9adb653fe351778c9b3"}, {file = "pyarrow-13.0.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:e66442e084979a97bb66939e18f7b8709e4ac5f887e636aba29486ffbf373763"},
{file = "pyarrow-12.0.1-cp39-cp39-macosx_10_14_x86_64.whl", hash = "sha256:a3c63124fc26bf5f95f508f5d04e1ece8cc23a8b0af2a1e6ab2b1ec3fdc91b24"}, {file = "pyarrow-13.0.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:0f6eff839a9e40e9c5610d3ff8c5bdd2f10303408312caf4c8003285d0b49565"},
{file = "pyarrow-12.0.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:b13329f79fa4472324f8d32dc1b1216616d09bd1e77cfb13104dec5463632c36"}, {file = "pyarrow-13.0.0-cp38-cp38-win_amd64.whl", hash = "sha256:8b30a27f1cddf5c6efcb67e598d7823a1e253d743d92ac32ec1eb4b6a1417867"},
{file = "pyarrow-12.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bb656150d3d12ec1396f6dde542db1675a95c0cc8366d507347b0beed96e87ca"}, {file = "pyarrow-13.0.0-cp39-cp39-macosx_10_14_x86_64.whl", hash = "sha256:09552dad5cf3de2dc0aba1c7c4b470754c69bd821f5faafc3d774bedc3b04bb7"},
{file = "pyarrow-12.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6251e38470da97a5b2e00de5c6a049149f7b2bd62f12fa5dbb9ac674119ba71a"}, {file = "pyarrow-13.0.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:3896ae6c205d73ad192d2fc1489cd0edfab9f12867c85b4c277af4d37383c18c"},
{file = "pyarrow-12.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:3de26da901216149ce086920547dfff5cd22818c9eab67ebc41e863a5883bac7"}, {file = "pyarrow-13.0.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6647444b21cb5e68b593b970b2a9a07748dd74ea457c7dadaa15fd469c48ada1"},
{file = "pyarrow-12.0.1.tar.gz", hash = "sha256:cce317fc96e5b71107bf1f9f184d5e54e2bd14bbf3f9a3d62819961f0af86fec"}, {file = "pyarrow-13.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:47663efc9c395e31d09c6aacfa860f4473815ad6804311c5433f7085415d62a7"},
{file = "pyarrow-13.0.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:b9ba6b6d34bd2563345488cf444510588ea42ad5613df3b3509f48eb80250afd"},
{file = "pyarrow-13.0.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:d00d374a5625beeb448a7fa23060df79adb596074beb3ddc1838adb647b6ef09"},
{file = "pyarrow-13.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:c51afd87c35c8331b56f796eff954b9c7f8d4b7fef5903daf4e05fcf017d23a8"},
{file = "pyarrow-13.0.0.tar.gz", hash = "sha256:83333726e83ed44b0ac94d8d7a21bbdee4a05029c3b1e8db58a863eec8fd8a33"},
] ]
[package.dependencies] [package.dependencies]
@ -1566,6 +1574,7 @@ files = [
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"}, {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"},
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"}, {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"},
{file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"}, {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"},
{file = "PyYAML-6.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:326c013efe8048858a6d312ddd31d56e468118ad4cdeda36c719bf5bb6192290"},
{file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"}, {file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"},
{file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"}, {file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"},
{file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"}, {file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"},
@ -1573,8 +1582,15 @@ files = [
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"}, {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"},
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"}, {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"},
{file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"}, {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"},
{file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"},
{file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"}, {file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"},
{file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"}, {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
{file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
{file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
{file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
{file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
{file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},
{file = "PyYAML-6.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:0d3304d8c0adc42be59c5f8a4d9e3d7379e6955ad754aa9d6ab7a398b59dd1df"},
{file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"}, {file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"},
{file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"}, {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"},
{file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"}, {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"},
@ -1591,6 +1607,7 @@ files = [
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"}, {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"},
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"}, {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"},
{file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"}, {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"},
{file = "PyYAML-6.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49a183be227561de579b4a36efbb21b3eab9651dd81b1858589f796549873dd6"},
{file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"}, {file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"},
{file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"}, {file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"},
{file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"}, {file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"},
@ -1598,6 +1615,7 @@ files = [
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"}, {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"},
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"}, {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"},
{file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"}, {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"},
{file = "PyYAML-6.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:04ac92ad1925b2cff1db0cfebffb6ffc43457495c9b3c39d3fcae417d7125dc5"},
{file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"}, {file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"},
{file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"}, {file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"},
{file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"}, {file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"},
@ -1723,93 +1741,115 @@ use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
[[package]] [[package]]
name = "safetensors" name = "safetensors"
version = "0.3.2" version = "0.3.3"
description = "Fast and Safe Tensor serialization" description = "Fast and Safe Tensor serialization"
optional = false optional = false
python-versions = "*" python-versions = "*"
files = [ files = [
{file = "safetensors-0.3.2-cp310-cp310-macosx_11_0_x86_64.whl", hash = "sha256:b6a66989075c2891d743153e8ba9ca84ee7232c8539704488f454199b8b8f84d"}, {file = "safetensors-0.3.3-cp310-cp310-macosx_10_11_x86_64.whl", hash = "sha256:92e4d0c8b2836120fddd134474c5bda8963f322333941f8b9f643e5b24f041eb"},
{file = "safetensors-0.3.2-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:670d6bc3a3b377278ce2971fa7c36ebc0a35041c4ea23b9df750a39380800195"}, {file = "safetensors-0.3.3-cp310-cp310-macosx_11_0_x86_64.whl", hash = "sha256:3dcadb6153c42addc9c625a622ebde9293fabe1973f9ef31ba10fb42c16e8536"},
{file = "safetensors-0.3.2-cp310-cp310-macosx_13_0_arm64.whl", hash = "sha256:564f42838721925b5313ae864ba6caa6f4c80a9fbe63cf24310c3be98ab013cd"}, {file = "safetensors-0.3.3-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:08f26b61e1b0a14dc959aa9d568776bd038805f611caef1de04a80c468d4a7a4"},
{file = "safetensors-0.3.2-cp310-cp310-macosx_13_0_x86_64.whl", hash = "sha256:7f80af7e4ab3188daaff12d43d078da3017a90d732d38d7af4eb08b6ca2198a5"}, {file = "safetensors-0.3.3-cp310-cp310-macosx_12_0_x86_64.whl", hash = "sha256:17f41344d9a075f2f21b289a49a62e98baff54b5754240ba896063bce31626bf"},
{file = "safetensors-0.3.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ec30d78f20f1235b252d59cbb9755beb35a1fde8c24c89b3c98e6a1804cfd432"}, {file = "safetensors-0.3.3-cp310-cp310-macosx_13_0_arm64.whl", hash = "sha256:f1045f798e1a16a6ced98d6a42ec72936d367a2eec81dc5fade6ed54638cd7d2"},
{file = "safetensors-0.3.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:16063d94d8f600768d3c331b1e97964b1bf3772e19710105fe24ec5a6af63770"}, {file = "safetensors-0.3.3-cp310-cp310-macosx_13_0_x86_64.whl", hash = "sha256:eaf0e4bc91da13f21ac846a39429eb3f3b7ed06295a32321fa3eb1a59b5c70f3"},
{file = "safetensors-0.3.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cbb44e140bf2aeda98d9dde669dbec15f7b77f96a9274469b91a6cf4bcc5ec3b"}, {file = "safetensors-0.3.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:25149180d4dc8ca48bac2ac3852a9424b466e36336a39659b35b21b2116f96fc"},
{file = "safetensors-0.3.2-cp310-cp310-win32.whl", hash = "sha256:2961c1243fd0da46aa6a1c835305cc4595486f8ac64632a604d0eb5f2de76175"}, {file = "safetensors-0.3.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c9e943bf78c39de8865398a71818315e7d5d1af93c7b30d4da3fc852e62ad9bc"},
{file = "safetensors-0.3.2-cp310-cp310-win_amd64.whl", hash = "sha256:c813920482c337d1424d306e1b05824a38e3ef94303748a0a287dea7a8c4f805"}, {file = "safetensors-0.3.3-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cccfcac04a010354e87c7a2fe16a1ff004fc4f6e7ef8efc966ed30122ce00bc7"},
{file = "safetensors-0.3.2-cp311-cp311-macosx_10_11_universal2.whl", hash = "sha256:707df34bd9b9047e97332136ad98e57028faeccdb9cfe1c3b52aba5964cc24bf"}, {file = "safetensors-0.3.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a07121f427e646a50d18c1be0fa1a2cbf6398624c31149cd7e6b35486d72189e"},
{file = "safetensors-0.3.2-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:becc5bb85b2947eae20ed23b407ebfd5277d9a560f90381fe2c42e6c043677ba"}, {file = "safetensors-0.3.3-cp310-cp310-win32.whl", hash = "sha256:a85e29cbfddfea86453cc0f4889b4bcc6b9c155be9a60e27be479a34e199e7ef"},
{file = "safetensors-0.3.2-cp311-cp311-macosx_13_0_arm64.whl", hash = "sha256:30a75707be5cc9686490bde14b9a371cede4af53244ea72b340cfbabfffdf58a"}, {file = "safetensors-0.3.3-cp310-cp310-win_amd64.whl", hash = "sha256:e13adad4a3e591378f71068d14e92343e626cf698ff805f61cdb946e684a218e"},
{file = "safetensors-0.3.2-cp311-cp311-macosx_13_0_universal2.whl", hash = "sha256:54ad6af663e15e2b99e2ea3280981b7514485df72ba6d014dc22dae7ba6a5e6c"}, {file = "safetensors-0.3.3-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:cbc3312f134baf07334dd517341a4b470b2931f090bd9284888acb7dfaf4606f"},
{file = "safetensors-0.3.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:37764b3197656ef507a266c453e909a3477dabc795962b38e3ad28226f53153b"}, {file = "safetensors-0.3.3-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:d15030af39d5d30c22bcbc6d180c65405b7ea4c05b7bab14a570eac7d7d43722"},
{file = "safetensors-0.3.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4939067736783acd8391d83cd97d6c202f94181951ce697d519f9746381b6a39"}, {file = "safetensors-0.3.3-cp311-cp311-macosx_12_0_universal2.whl", hash = "sha256:f84a74cbe9859b28e3d6d7715ac1dd3097bebf8d772694098f6d42435245860c"},
{file = "safetensors-0.3.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ada0fac127ff8fb04834da5c6d85a8077e6a1c9180a11251d96f8068db922a17"}, {file = "safetensors-0.3.3-cp311-cp311-macosx_13_0_arm64.whl", hash = "sha256:10d637423d98ab2e6a4ad96abf4534eb26fcaf8ca3115623e64c00759374e90d"},
{file = "safetensors-0.3.2-cp311-cp311-win32.whl", hash = "sha256:155b82dbe2b0ebff18cde3f76b42b6d9470296e92561ef1a282004d449fa2b4c"}, {file = "safetensors-0.3.3-cp311-cp311-macosx_13_0_universal2.whl", hash = "sha256:3b46f5de8b44084aff2e480874c550c399c730c84b2e8ad1bddb062c94aa14e9"},
{file = "safetensors-0.3.2-cp311-cp311-win_amd64.whl", hash = "sha256:a86428d196959619ce90197731be9391b5098b35100a7228ef4643957648f7f5"}, {file = "safetensors-0.3.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e76da691a82dfaf752854fa6d17c8eba0c8466370c5ad8cf1bfdf832d3c7ee17"},
{file = "safetensors-0.3.2-cp37-cp37m-macosx_11_0_x86_64.whl", hash = "sha256:c1f8ab41ed735c5b581f451fd15d9602ff51aa88044bfa933c5fa4b1d0c644d1"}, {file = "safetensors-0.3.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c4e342fd54e66aa9512dd13e410f791e47aa4feeb5f4c9a20882c72f3d272f29"},
{file = "safetensors-0.3.2-cp37-cp37m-macosx_13_0_x86_64.whl", hash = "sha256:bc9cfb3c9ea2aec89685b4d656f9f2296f0f0d67ecf2bebf950870e3be89b3db"}, {file = "safetensors-0.3.3-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:178fd30b5dc73bce14a39187d948cedd0e5698e2f055b7ea16b5a96c9b17438e"},
{file = "safetensors-0.3.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ace5d471e3d78e0d93f952707d808b5ab5eac77ddb034ceb702e602e9acf2be9"}, {file = "safetensors-0.3.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3e8fdf7407dba44587ed5e79d5de3533d242648e1f2041760b21474bd5ea5c8c"},
{file = "safetensors-0.3.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:de3e20a388b444381bcda1a3193cce51825ddca277e4cf3ed1fe8d9b2d5722cd"}, {file = "safetensors-0.3.3-cp311-cp311-win32.whl", hash = "sha256:7d3b744cee8d7a46ffa68db1a2ff1a1a432488e3f7a5a97856fe69e22139d50c"},
{file = "safetensors-0.3.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3d7d70d48585fe8df00725aa788f2e64fd24a4c9ae07cd6be34f6859d0f89a9c"}, {file = "safetensors-0.3.3-cp311-cp311-win_amd64.whl", hash = "sha256:f579877d30feec9b6ba409d05fa174633a4fc095675a4a82971d831a8bb60b97"},
{file = "safetensors-0.3.2-cp37-cp37m-win32.whl", hash = "sha256:6ff59bc90cdc857f68b1023be9085fda6202bbe7f2fd67d06af8f976d6adcc10"}, {file = "safetensors-0.3.3-cp37-cp37m-macosx_10_11_x86_64.whl", hash = "sha256:2fff5b19a1b462c17322998b2f4b8bce43c16fe208968174d2f3a1446284ceed"},
{file = "safetensors-0.3.2-cp37-cp37m-win_amd64.whl", hash = "sha256:8b05c93da15fa911763a89281906ca333ed800ab0ef1c7ce53317aa1a2322f19"}, {file = "safetensors-0.3.3-cp37-cp37m-macosx_11_0_x86_64.whl", hash = "sha256:41adb1d39e8aad04b16879e3e0cbcb849315999fad73bc992091a01e379cb058"},
{file = "safetensors-0.3.2-cp38-cp38-macosx_11_0_x86_64.whl", hash = "sha256:8969cfd9e8d904e8d3c67c989e1bd9a95e3cc8980d4f95e4dcd43c299bb94253"}, {file = "safetensors-0.3.3-cp37-cp37m-macosx_12_0_x86_64.whl", hash = "sha256:0f2b404250b3b877b11d34afcc30d80e7035714a1116a3df56acaca6b6c00096"},
{file = "safetensors-0.3.2-cp38-cp38-macosx_13_0_x86_64.whl", hash = "sha256:f54148ac027556eb02187e9bc1556c4d916c99ca3cb34ca36a7d304d675035c1"}, {file = "safetensors-0.3.3-cp37-cp37m-macosx_13_0_x86_64.whl", hash = "sha256:b43956ef20e9f4f2e648818a9e7b3499edd6b753a0f5526d4f6a6826fbee8446"},
{file = "safetensors-0.3.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:caec25fedbcf73f66c9261984f07885680f71417fc173f52279276c7f8a5edd3"}, {file = "safetensors-0.3.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d61a99b34169981f088ccfbb2c91170843efc869a0a0532f422db7211bf4f474"},
{file = "safetensors-0.3.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:50224a1d99927ccf3b75e27c3d412f7043280431ab100b4f08aad470c37cf99a"}, {file = "safetensors-0.3.3-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c0008aab36cd20e9a051a68563c6f80d40f238c2611811d7faa5a18bf3fd3984"},
{file = "safetensors-0.3.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aa98f49e95f02eb750d32c4947e7d5aa43883149ebd0414920866446525b70f0"}, {file = "safetensors-0.3.3-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:93d54166072b143084fdcd214a080a088050c1bb1651016b55942701b31334e4"},
{file = "safetensors-0.3.2-cp38-cp38-win32.whl", hash = "sha256:33409df5e28a83dc5cc5547a3ac17c0f1b13a1847b1eb3bc4b3be0df9915171e"}, {file = "safetensors-0.3.3-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1c32ee08f61cea56a5d62bbf94af95df6040c8ab574afffaeb7b44ae5da1e9e3"},
{file = "safetensors-0.3.2-cp38-cp38-win_amd64.whl", hash = "sha256:e04a7cbbb3856159ab99e3adb14521544f65fcb8548cce773a1435a0f8d78d27"}, {file = "safetensors-0.3.3-cp37-cp37m-win32.whl", hash = "sha256:351600f367badd59f7bfe86d317bb768dd8c59c1561c6fac43cafbd9c1af7827"},
{file = "safetensors-0.3.2-cp39-cp39-macosx_11_0_x86_64.whl", hash = "sha256:7c864cf5dcbfb608c5378f83319c60cc9c97263343b57c02756b7613cd5ab4dd"}, {file = "safetensors-0.3.3-cp37-cp37m-win_amd64.whl", hash = "sha256:034717e297849dae1af0a7027a14b8647bd2e272c24106dced64d83e10d468d1"},
{file = "safetensors-0.3.2-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:14e8c19d6dc51d4f70ee33c46aff04c8ba3f95812e74daf8036c24bc86e75cae"}, {file = "safetensors-0.3.3-cp38-cp38-macosx_10_11_x86_64.whl", hash = "sha256:8530399666748634bc0b301a6a5523756931b0c2680d188e743d16304afe917a"},
{file = "safetensors-0.3.2-cp39-cp39-macosx_13_0_arm64.whl", hash = "sha256:042a60f633c3c7009fdf6a7c182b165cb7283649d2a1e9c7a4a1c23454bd9a5b"}, {file = "safetensors-0.3.3-cp38-cp38-macosx_11_0_x86_64.whl", hash = "sha256:9d741c1f1621e489ba10aa3d135b54202684f6e205df52e219d5eecd673a80c9"},
{file = "safetensors-0.3.2-cp39-cp39-macosx_13_0_x86_64.whl", hash = "sha256:fafd95e5ef41e8f312e2a32b7031f7b9b2a621b255f867b221f94bb2e9f51ae8"}, {file = "safetensors-0.3.3-cp38-cp38-macosx_12_0_arm64.whl", hash = "sha256:0c345fd85b4d2093a5109596ff4cd9dfc2e84992e881b4857fbc4a93a3b89ddb"},
{file = "safetensors-0.3.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8ed77cf358abce2307f03634694e0b2a29822e322a1623e0b1aa4b41e871bf8b"}, {file = "safetensors-0.3.3-cp38-cp38-macosx_12_0_x86_64.whl", hash = "sha256:69ccee8d05f55cdf76f7e6c87d2bdfb648c16778ef8acfd2ecc495e273e9233e"},
{file = "safetensors-0.3.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5d344e8b2681a33aafc197c90b0def3229b3317d749531c72fa6259d0caa5c8c"}, {file = "safetensors-0.3.3-cp38-cp38-macosx_13_0_arm64.whl", hash = "sha256:c08a9a4b7a4ca389232fa8d097aebc20bbd4f61e477abc7065b5c18b8202dede"},
{file = "safetensors-0.3.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:87ff0024ef2e5722a79af24688ce4a430f70601d0cf712a744105ed4b8f67ba5"}, {file = "safetensors-0.3.3-cp38-cp38-macosx_13_0_x86_64.whl", hash = "sha256:a002868d2e3f49bbe81bee2655a411c24fa1f8e68b703dec6629cb989d6ae42e"},
{file = "safetensors-0.3.2-cp39-cp39-win32.whl", hash = "sha256:827af9478b78977248ba93e2fd97ea307fb63f463f80cef4824460f8c2542a52"}, {file = "safetensors-0.3.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3bd2704cb41faa44d3ec23e8b97330346da0395aec87f8eaf9c9e2c086cdbf13"},
{file = "safetensors-0.3.2-cp39-cp39-win_amd64.whl", hash = "sha256:9b09f27c456efa301f98681ea14b12f81f2637889f6336223ccab71e42c34541"}, {file = "safetensors-0.3.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4b2951bf3f0ad63df5e6a95263652bd6c194a6eb36fd4f2d29421cd63424c883"},
{file = "safetensors-0.3.2.tar.gz", hash = "sha256:2dbd34554ed3b99435a0e84df077108f5334c8336b5ed9cb8b6b98f7b10da2f6"}, {file = "safetensors-0.3.3-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:07114cec116253ca2e7230fdea30acf76828f21614afd596d7b5438a2f719bd8"},
{file = "safetensors-0.3.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6ab43aeeb9eadbb6b460df3568a662e6f1911ecc39387f8752afcb6a7d96c087"},
{file = "safetensors-0.3.3-cp38-cp38-win32.whl", hash = "sha256:f2f59fce31dd3429daca7269a6b06f65e6547a0c248f5116976c3f1e9b73f251"},
{file = "safetensors-0.3.3-cp38-cp38-win_amd64.whl", hash = "sha256:c31ca0d8610f57799925bf08616856b39518ab772c65093ef1516762e796fde4"},
{file = "safetensors-0.3.3-cp39-cp39-macosx_10_11_x86_64.whl", hash = "sha256:59a596b3225c96d59af412385981f17dd95314e3fffdf359c7e3f5bb97730a19"},
{file = "safetensors-0.3.3-cp39-cp39-macosx_11_0_x86_64.whl", hash = "sha256:82a16e92210a6221edd75ab17acdd468dd958ef5023d9c6c1289606cc30d1479"},
{file = "safetensors-0.3.3-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:98a929e763a581f516373ef31983ed1257d2d0da912a8e05d5cd12e9e441c93a"},
{file = "safetensors-0.3.3-cp39-cp39-macosx_12_0_x86_64.whl", hash = "sha256:12b83f1986cd16ea0454c636c37b11e819d60dd952c26978310a0835133480b7"},
{file = "safetensors-0.3.3-cp39-cp39-macosx_13_0_arm64.whl", hash = "sha256:f439175c827c2f1bbd54df42789c5204a10983a30bc4242bc7deaf854a24f3f0"},
{file = "safetensors-0.3.3-cp39-cp39-macosx_13_0_x86_64.whl", hash = "sha256:0085be33b8cbcb13079b3a8e131656e05b0bc5e6970530d4c24150f7afd76d70"},
{file = "safetensors-0.3.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3e3ec70c87b1e910769034206ad5efc051069b105aac1687f6edcd02526767f4"},
{file = "safetensors-0.3.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f490132383e5e490e710608f4acffcb98ed37f91b885c7217d3f9f10aaff9048"},
{file = "safetensors-0.3.3-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:79d1b6c7ed5596baf79c80fbce5198c3cdcc521ae6a157699f427aba1a90082d"},
{file = "safetensors-0.3.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ad3cc8006e7a86ee7c88bd2813ec59cd7cc75b03e6fa4af89b9c7b235b438d68"},
{file = "safetensors-0.3.3-cp39-cp39-win32.whl", hash = "sha256:ab29f54c6b8c301ca05fa014728996bd83aac6e21528f893aaf8945c71f42b6d"},
{file = "safetensors-0.3.3-cp39-cp39-win_amd64.whl", hash = "sha256:0fa82004eae1a71e2aa29843ef99de9350e459a0fc2f65fc6ee0da9690933d2d"},
{file = "safetensors-0.3.3.tar.gz", hash = "sha256:edb7072d788c4f929d0f5735d3a2fb51e5a27f833587828583b7f5747af1a2b8"},
] ]
[package.extras] [package.extras]
all = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "flax (>=0.6.3)", "h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "isort (>=5.5.4)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "numpy (>=1.21.6)", "paddlepaddle (>=2.4.1)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)", "tensorflow (==2.11.0)", "torch (>=1.10)"] all = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "flax (>=0.6.3)", "h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "isort (>=5.5.4)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "numpy (>=1.21.6)", "paddlepaddle (>=2.4.1)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)", "tensorflow (==2.11.0)", "torch (>=1.10)"]
dev = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "flax (>=0.6.3)", "h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "isort (>=5.5.4)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "numpy (>=1.21.6)", "paddlepaddle (>=2.4.1)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)", "tensorflow (==2.11.0)", "torch (>=1.10)"] dev = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "flax (>=0.6.3)", "h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "isort (>=5.5.4)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "numpy (>=1.21.6)", "paddlepaddle (>=2.4.1)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)", "tensorflow (==2.11.0)", "torch (>=1.10)"]
jax = ["flax (>=0.6.3)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)"] jax = ["flax (>=0.6.3)", "jax (>=0.3.25)", "jaxlib (>=0.3.25)", "numpy (>=1.21.6)"]
numpy = ["numpy (>=1.21.6)"] numpy = ["numpy (>=1.21.6)"]
paddlepaddle = ["paddlepaddle (>=2.4.1)"] paddlepaddle = ["numpy (>=1.21.6)", "paddlepaddle (>=2.4.1)"]
pinned-tf = ["tensorflow (==2.11.0)"] pinned-tf = ["tensorflow (==2.11.0)"]
quality = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "isort (>=5.5.4)"] quality = ["black (==22.3)", "click (==8.0.4)", "flake8 (>=3.8.3)", "isort (>=5.5.4)"]
tensorflow = ["tensorflow (>=2.11.0)"] tensorflow = ["numpy (>=1.21.6)", "tensorflow (>=2.11.0)"]
testing = ["h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "numpy (>=1.21.6)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)"] testing = ["h5py (>=3.7.0)", "huggingface-hub (>=0.12.1)", "numpy (>=1.21.6)", "pytest (>=7.2.0)", "pytest-benchmark (>=4.0.0)", "setuptools-rust (>=1.5.2)"]
torch = ["torch (>=1.10)"] torch = ["numpy (>=1.21.6)", "torch (>=1.10)"]
[[package]] [[package]]
name = "scipy" name = "scipy"
version = "1.11.1" version = "1.11.2"
description = "Fundamental algorithms for scientific computing in Python" description = "Fundamental algorithms for scientific computing in Python"
optional = false optional = false
python-versions = "<3.13,>=3.9" python-versions = "<3.13,>=3.9"
files = [ files = [
{file = "scipy-1.11.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:aec8c62fbe52914f9cf28d846cf0401dd80ab80788bbab909434eb336ed07c04"}, {file = "scipy-1.11.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:2b997a5369e2d30c97995dcb29d638701f8000d04df01b8e947f206e5d0ac788"},
{file = "scipy-1.11.1-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:3b9963798df1d8a52db41a6fc0e6fa65b1c60e85d73da27ae8bb754de4792481"}, {file = "scipy-1.11.2-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:95763fbda1206bec41157582bea482f50eb3702c85fffcf6d24394b071c0e87a"},
{file = "scipy-1.11.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3e8eb42db36526b130dfbc417609498a6192381abc1975b91e3eb238e0b41c1a"}, {file = "scipy-1.11.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e367904a0fec76433bf3fbf3e85bf60dae8e9e585ffd21898ab1085a29a04d16"},
{file = "scipy-1.11.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:366a6a937110d80dca4f63b3f5b00cc89d36f678b2d124a01067b154e692bab1"}, {file = "scipy-1.11.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d690e1ca993c8f7ede6d22e5637541217fc6a4d3f78b3672a6fe454dbb7eb9a7"},
{file = "scipy-1.11.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:08d957ca82d3535b3b9ba6c8ff355d78fe975271874e2af267cb5add5bd78625"}, {file = "scipy-1.11.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:d2b813bfbe8dec6a75164523de650bad41f4405d35b0fa24c2c28ae07fcefb20"},
{file = "scipy-1.11.1-cp310-cp310-win_amd64.whl", hash = "sha256:e866514bc2d660608447b6ba95c8900d591f2865c07cca0aa4f7ff3c4ca70f30"}, {file = "scipy-1.11.2-cp310-cp310-win_amd64.whl", hash = "sha256:afdb0d983f6135d50770dd979df50bf1c7f58b5b33e0eb8cf5c73c70600eae1d"},
{file = "scipy-1.11.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:ba94eeef3c9caa4cea7b402a35bb02a5714ee1ee77eb98aca1eed4543beb0f4c"}, {file = "scipy-1.11.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:8d9886f44ef8c9e776cb7527fb01455bf4f4a46c455c4682edc2c2cc8cd78562"},
{file = "scipy-1.11.1-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:512fdc18c65f76dadaca139348e525646d440220d8d05f6d21965b8d4466bccd"}, {file = "scipy-1.11.2-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:1342ca385c673208f32472830c10110a9dcd053cf0c4b7d4cd7026d0335a6c1d"},
{file = "scipy-1.11.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cce154372f0ebe88556ed06d7b196e9c2e0c13080ecb58d0f35062dc7cc28b47"}, {file = "scipy-1.11.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b133f237bd8ba73bad51bc12eb4f2d84cbec999753bf25ba58235e9fc2096d80"},
{file = "scipy-1.11.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b4bb943010203465ac81efa392e4645265077b4d9e99b66cf3ed33ae12254173"}, {file = "scipy-1.11.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3aeb87661de987f8ec56fa6950863994cd427209158255a389fc5aea51fa7055"},
{file = "scipy-1.11.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:249cfa465c379c9bb2c20123001e151ff5e29b351cbb7f9c91587260602c58d0"}, {file = "scipy-1.11.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:90d3b1364e751d8214e325c371f0ee0dd38419268bf4888b2ae1040a6b266b2a"},
{file = "scipy-1.11.1-cp311-cp311-win_amd64.whl", hash = "sha256:ffb28e3fa31b9c376d0fb1f74c1f13911c8c154a760312fbee87a21eb21efe31"}, {file = "scipy-1.11.2-cp311-cp311-win_amd64.whl", hash = "sha256:f73102f769ee06041a3aa26b5841359b1a93cc364ce45609657751795e8f4a4a"},
{file = "scipy-1.11.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:39154437654260a52871dfde852adf1b93b1d1bc5dc0ffa70068f16ec0be2624"}, {file = "scipy-1.11.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:fa4909c6c20c3d91480533cddbc0e7c6d849e7d9ded692918c76ce5964997898"},
{file = "scipy-1.11.1-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:b588311875c58d1acd4ef17c983b9f1ab5391755a47c3d70b6bd503a45bfaf71"}, {file = "scipy-1.11.2-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:ac74b1512d38718fb6a491c439aa7b3605b96b1ed3be6599c17d49d6c60fca18"},
{file = "scipy-1.11.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d51565560565a0307ed06fa0ec4c6f21ff094947d4844d6068ed04400c72d0c3"}, {file = "scipy-1.11.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b8425fa963a32936c9773ee3ce44a765d8ff67eed5f4ac81dc1e4a819a238ee9"},
{file = "scipy-1.11.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b41a0f322b4eb51b078cb3441e950ad661ede490c3aca66edef66f4b37ab1877"}, {file = "scipy-1.11.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:542a757e2a6ec409e71df3d8fd20127afbbacb1c07990cb23c5870c13953d899"},
{file = "scipy-1.11.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:396fae3f8c12ad14c5f3eb40499fd06a6fef8393a6baa352a652ecd51e74e029"}, {file = "scipy-1.11.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:ea932570b1c2a30edafca922345854ff2cd20d43cd9123b6dacfdecebfc1a80b"},
{file = "scipy-1.11.1-cp39-cp39-win_amd64.whl", hash = "sha256:be8c962a821957fdde8c4044efdab7a140c13294997a407eaee777acf63cbf0c"}, {file = "scipy-1.11.2-cp312-cp312-win_amd64.whl", hash = "sha256:4447ad057d7597476f9862ecbd9285bbf13ba9d73ce25acfa4e4b11c6801b4c9"},
{file = "scipy-1.11.1.tar.gz", hash = "sha256:fb5b492fa035334fd249f0973cc79ecad8b09c604b42a127a677b45a9a3d4289"}, {file = "scipy-1.11.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:b0620240ef445b5ddde52460e6bc3483b7c9c750275369379e5f609a1050911c"},
{file = "scipy-1.11.2-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:f28f1f6cfeb48339c192efc6275749b2a25a7e49c4d8369a28b6591da02fbc9a"},
{file = "scipy-1.11.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:214cdf04bbae7a54784f8431f976704ed607c4bc69ba0d5d5d6a9df84374df76"},
{file = "scipy-1.11.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:10eb6af2f751aa3424762948e5352f707b0dece77288206f227864ddf675aca0"},
{file = "scipy-1.11.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:0f3261f14b767b316d7137c66cc4f33a80ea05841b9c87ad83a726205b901423"},
{file = "scipy-1.11.2-cp39-cp39-win_amd64.whl", hash = "sha256:2c91cf049ffb5575917f2a01da1da082fd24ed48120d08a6e7297dfcac771dcd"},
{file = "scipy-1.11.2.tar.gz", hash = "sha256:b29318a5e39bd200ca4381d80b065cdf3076c7d7281c5e36569e99273867f61d"},
] ]
[package.dependencies] [package.dependencies]
@ -1876,18 +1916,18 @@ files = [
[[package]] [[package]]
name = "setuptools" name = "setuptools"
version = "68.0.0" version = "68.1.2"
description = "Easily download, build, install, upgrade, and uninstall Python packages" description = "Easily download, build, install, upgrade, and uninstall Python packages"
optional = false optional = false
python-versions = ">=3.7" python-versions = ">=3.8"
files = [ files = [
{file = "setuptools-68.0.0-py3-none-any.whl", hash = "sha256:11e52c67415a381d10d6b462ced9cfb97066179f0e871399e006c4ab101fc85f"}, {file = "setuptools-68.1.2-py3-none-any.whl", hash = "sha256:3d8083eed2d13afc9426f227b24fd1659489ec107c0e86cec2ffdde5c92e790b"},
{file = "setuptools-68.0.0.tar.gz", hash = "sha256:baf1fdb41c6da4cd2eae722e135500da913332ab3f2f5c7d33af9b492acb5235"}, {file = "setuptools-68.1.2.tar.gz", hash = "sha256:3d4dfa6d95f1b101d695a6160a7626e15583af71a5f52176efa5d39a054d475d"},
] ]
[package.extras] [package.extras]
docs = ["furo", "jaraco.packaging (>=9)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-hoverxref (<2)", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (==0.8.3)", "sphinx-reredirects", "sphinxcontrib-towncrier"] docs = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "rst.linker (>=1.9)", "sphinx (>=3.5,<=7.1.2)", "sphinx-favicon", "sphinx-hoverxref (<2)", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (==0.8.3)", "sphinx-reredirects", "sphinxcontrib-towncrier"]
testing = ["build[virtualenv]", "filelock (>=3.4.0)", "flake8-2020", "ini2toml[lite] (>=0.9)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "pip (>=19.1)", "pip-run (>=8.8)", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=1.3)", "pytest-mypy (>=0.9.1)", "pytest-perf", "pytest-ruff", "pytest-timeout", "pytest-xdist", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"] testing = ["build[virtualenv]", "filelock (>=3.4.0)", "flake8-2020", "ini2toml[lite] (>=0.9)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "pip (>=19.1)", "pytest (>=6)", "pytest-black (>=0.3.7)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-mypy (>=0.9.1)", "pytest-perf", "pytest-ruff", "pytest-timeout", "pytest-xdist", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel"]
testing-integration = ["build[virtualenv]", "filelock (>=3.4.0)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "pytest", "pytest-enabler", "pytest-xdist", "tomli", "virtualenv (>=13.0.0)", "wheel"] testing-integration = ["build[virtualenv]", "filelock (>=3.4.0)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "pytest", "pytest-enabler", "pytest-xdist", "tomli", "virtualenv (>=13.0.0)", "wheel"]
[[package]] [[package]]
@ -2052,18 +2092,18 @@ telegram = ["requests"]
[[package]] [[package]]
name = "transformers" name = "transformers"
version = "4.31.0" version = "4.32.1"
description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow" description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
optional = false optional = false
python-versions = ">=3.8.0" python-versions = ">=3.8.0"
files = [ files = [
{file = "transformers-4.31.0-py3-none-any.whl", hash = "sha256:8487aab0195ce1c2a5ae189305118b9720daddbc7b688edb09ccd79e3b149f6b"}, {file = "transformers-4.32.1-py3-none-any.whl", hash = "sha256:b930d3dbd907a3f300cf49e54d63a56f8a0ab16b01a2c2a61ecff37c6de1da08"},
{file = "transformers-4.31.0.tar.gz", hash = "sha256:4302fba920a1c24d3a429a29efff6a63eac03f3f3cf55b55927fc795d01cb273"}, {file = "transformers-4.32.1.tar.gz", hash = "sha256:1edc8ae1de357d97c3d36b04412aa63d55e6fc0c4b39b419a7d380ed947d2252"},
] ]
[package.dependencies] [package.dependencies]
filelock = "*" filelock = "*"
huggingface-hub = ">=0.14.1,<1.0" huggingface-hub = ">=0.15.1,<1.0"
numpy = ">=1.17" numpy = ">=1.17"
packaging = ">=20.0" packaging = ">=20.0"
pyyaml = ">=5.1" pyyaml = ">=5.1"
@ -2076,18 +2116,18 @@ tqdm = ">=4.27"
[package.extras] [package.extras]
accelerate = ["accelerate (>=0.20.3)"] accelerate = ["accelerate (>=0.20.3)"]
agents = ["Pillow (<10.0.0)", "accelerate (>=0.20.3)", "datasets (!=2.5.0)", "diffusers", "opencv-python", "sentencepiece (>=0.1.91,!=0.1.92)", "torch (>=1.9,!=1.12.0)"] agents = ["Pillow (<10.0.0)", "accelerate (>=0.20.3)", "datasets (!=2.5.0)", "diffusers", "opencv-python", "sentencepiece (>=0.1.91,!=0.1.92)", "torch (>=1.9,!=1.12.0)"]
all = ["Pillow (<10.0.0)", "accelerate (>=0.20.3)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "jax (>=0.2.8,!=0.3.2,<=0.4.13)", "jaxlib (>=0.1.65,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune]", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.6,<2.14)", "tensorflow-text (<2.14)", "tf2onnx", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision"] all = ["Pillow (<10.0.0)", "accelerate (>=0.20.3)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune]", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.6,<2.14)", "tensorflow-text (<2.14)", "tf2onnx", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision"]
audio = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"] audio = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
codecarbon = ["codecarbon (==1.2.0)"] codecarbon = ["codecarbon (==1.2.0)"]
deepspeed = ["accelerate (>=0.20.3)", "deepspeed (>=0.9.3)"] deepspeed = ["accelerate (>=0.20.3)", "deepspeed (>=0.9.3)"]
deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.20.3)", "beautifulsoup4", "black (>=23.1,<24.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "optuna", "parameterized", "protobuf", "psutil", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "timeout-decorator"] deepspeed-testing = ["GitPython (<3.1.19)", "accelerate (>=0.20.3)", "beautifulsoup4", "black (>=23.1,<24.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "deepspeed (>=0.9.3)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder (>=0.3.0)", "nltk", "optuna", "parameterized", "protobuf", "psutil", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "sentencepiece (>=0.1.91,!=0.1.92)", "timeout-decorator"]
dev = ["GitPython (<3.1.19)", "Pillow (<10.0.0)", "accelerate (>=0.20.3)", "av (==9.2.0)", "beautifulsoup4", "black (>=23.1,<24.0)", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "decord (==0.6.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flax (>=0.4.1,<=0.7.0)", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "jax (>=0.2.8,!=0.3.2,<=0.4.13)", "jaxlib (>=0.1.65,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "ray[tune]", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (>=0.0.241,<=0.0.259)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorflow (>=2.6,<2.14)", "tensorflow-text (<2.14)", "tf2onnx", "timeout-decorator", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"] dev = ["GitPython (<3.1.19)", "Pillow (<10.0.0)", "accelerate (>=0.20.3)", "av (==9.2.0)", "beautifulsoup4", "black (>=23.1,<24.0)", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "decord (==0.6.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "flax (>=0.4.1,<=0.7.0)", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "ray[tune]", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (>=0.0.241,<=0.0.259)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "tensorflow (>=2.6,<2.14)", "tensorflow-text (<2.14)", "tf2onnx", "timeout-decorator", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
dev-tensorflow = ["GitPython (<3.1.19)", "Pillow (<10.0.0)", "beautifulsoup4", "black (>=23.1,<24.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (>=0.0.241,<=0.0.259)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorflow (>=2.6,<2.14)", "tensorflow-text (<2.14)", "tf2onnx", "timeout-decorator", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "urllib3 (<2.0.0)"] dev-tensorflow = ["GitPython (<3.1.19)", "Pillow (<10.0.0)", "beautifulsoup4", "black (>=23.1,<24.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "isort (>=5.5.4)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "nltk", "onnxconverter-common", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (>=0.0.241,<=0.0.259)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "tensorflow (>=2.6,<2.14)", "tensorflow-text (<2.14)", "tf2onnx", "timeout-decorator", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "urllib3 (<2.0.0)"]
dev-torch = ["GitPython (<3.1.19)", "Pillow (<10.0.0)", "accelerate (>=0.20.3)", "beautifulsoup4", "black (>=23.1,<24.0)", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "kenlm", "librosa", "nltk", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "ray[tune]", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (>=0.0.241,<=0.0.259)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "timeout-decorator", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"] dev-torch = ["GitPython (<3.1.19)", "Pillow (<10.0.0)", "accelerate (>=0.20.3)", "beautifulsoup4", "black (>=23.1,<24.0)", "codecarbon (==1.2.0)", "cookiecutter (==1.7.3)", "datasets (!=2.5.0)", "dill (<0.3.5)", "evaluate (>=0.2.0)", "faiss-cpu", "fugashi (>=1.0)", "hf-doc-builder", "hf-doc-builder (>=0.3.0)", "ipadic (>=1.0.0,<2.0)", "isort (>=5.5.4)", "kenlm", "librosa", "nltk", "onnxruntime (>=1.4.0)", "onnxruntime-tools (>=1.4.2)", "optuna", "parameterized", "phonemizer", "protobuf", "psutil", "pyctcdecode (>=0.4.0)", "pytest (>=7.2.0)", "pytest-timeout", "pytest-xdist", "ray[tune]", "rhoknp (>=1.1.0,<1.3.1)", "rjieba", "rouge-score (!=0.0.7,!=0.0.8,!=0.1,!=0.1.1)", "ruff (>=0.0.241,<=0.0.259)", "sacrebleu (>=1.4.12,<2.0.0)", "sacremoses", "scikit-learn", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "sudachidict-core (>=20220729)", "sudachipy (>=0.6.6)", "timeout-decorator", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision", "unidic (>=1.0.2)", "unidic-lite (>=1.0.7)", "urllib3 (<2.0.0)"]
docs = ["Pillow (<10.0.0)", "accelerate (>=0.20.3)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "hf-doc-builder", "jax (>=0.2.8,!=0.3.2,<=0.4.13)", "jaxlib (>=0.1.65,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune]", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.6,<2.14)", "tensorflow-text (<2.14)", "tf2onnx", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision"] docs = ["Pillow (<10.0.0)", "accelerate (>=0.20.3)", "av (==9.2.0)", "codecarbon (==1.2.0)", "decord (==0.6.0)", "flax (>=0.4.1,<=0.7.0)", "hf-doc-builder", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "kenlm", "keras-nlp (>=0.3.1)", "librosa", "onnxconverter-common", "optax (>=0.0.8,<=0.1.4)", "optuna", "phonemizer", "protobuf", "pyctcdecode (>=0.4.0)", "ray[tune]", "sentencepiece (>=0.1.91,!=0.1.92)", "sigopt", "tensorflow (>=2.6,<2.14)", "tensorflow-text (<2.14)", "tf2onnx", "timm", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "torchaudio", "torchvision"]
docs-specific = ["hf-doc-builder"] docs-specific = ["hf-doc-builder"]
fairscale = ["fairscale (>0.3)"] fairscale = ["fairscale (>0.3)"]
flax = ["flax (>=0.4.1,<=0.7.0)", "jax (>=0.2.8,!=0.3.2,<=0.4.13)", "jaxlib (>=0.1.65,<=0.4.13)", "optax (>=0.0.8,<=0.1.4)"] flax = ["flax (>=0.4.1,<=0.7.0)", "jax (>=0.4.1,<=0.4.13)", "jaxlib (>=0.4.1,<=0.4.13)", "optax (>=0.0.8,<=0.1.4)"]
flax-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"] flax-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)"]
ftfy = ["ftfy"] ftfy = ["ftfy"]
integrations = ["optuna", "ray[tune]", "sigopt"] integrations = ["optuna", "ray[tune]", "sigopt"]
@ -2115,7 +2155,7 @@ tokenizers = ["tokenizers (>=0.11.1,!=0.11.3,<0.14)"]
torch = ["accelerate (>=0.20.3)", "torch (>=1.9,!=1.12.0)"] torch = ["accelerate (>=0.20.3)", "torch (>=1.9,!=1.12.0)"]
torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"] torch-speech = ["kenlm", "librosa", "phonemizer", "pyctcdecode (>=0.4.0)", "torchaudio"]
torch-vision = ["Pillow (<10.0.0)", "torchvision"] torch-vision = ["Pillow (<10.0.0)", "torchvision"]
torchhub = ["filelock", "huggingface-hub (>=0.14.1,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "tqdm (>=4.27)"] torchhub = ["filelock", "huggingface-hub (>=0.15.1,<1.0)", "importlib-metadata", "numpy (>=1.17)", "packaging (>=20.0)", "protobuf", "regex (!=2019.12.17)", "requests", "sentencepiece (>=0.1.91,!=0.1.92)", "tokenizers (>=0.11.1,!=0.11.3,<0.14)", "torch (>=1.9,!=1.12.0)", "tqdm (>=4.27)"]
video = ["av (==9.2.0)", "decord (==0.6.0)"] video = ["av (==9.2.0)", "decord (==0.6.0)"]
vision = ["Pillow (<10.0.0)"] vision = ["Pillow (<10.0.0)"]
@ -2465,4 +2505,4 @@ quantize = ["accelerate", "datasets", "texttable"]
[metadata] [metadata]
lock-version = "2.0" lock-version = "2.0"
python-versions = ">=3.9,<3.13" python-versions = ">=3.9,<3.13"
content-hash = "91a848038c08a44c67acfb4257781440ccc1e74a4b82f09513e75588fa33f72b" content-hash = "f2ef5f41a172d14985367a385ad6ce844c8c05b2d68d9ddcc11b41f581921c96"

6
server/pyproject.toml
View File

@ -1,6 +1,6 @@
[tool.poetry] [tool.poetry]
name = "text-generation-server" name = "text-generation-server"
version = "1.0.1" version = "1.0.3"
description = "Text Generation Inference Python gRPC Server" description = "Text Generation Inference Python gRPC Server"
authors = ["Olivier Dehaene <olivier@huggingface.co>"] authors = ["Olivier Dehaene <olivier@huggingface.co>"]
@ -25,8 +25,8 @@ opentelemetry-instrumentation-grpc = "^0.36b0"
hf-transfer = "^0.1.2" hf-transfer = "^0.1.2"
sentencepiece = "^0.1.97" sentencepiece = "^0.1.97"
tokenizers = "^0.13.3" tokenizers = "^0.13.3"
huggingface-hub = "^0.14.1" huggingface-hub = "^0.16.4"
transformers = "^4.31.0" transformers = "^4.32.1"
einops = "^0.6.1" einops = "^0.6.1"
texttable = { version = "^1.6.7", optional = true } texttable = { version = "^1.6.7", optional = true }
datasets = { version = "^2.14.0", optional = true } datasets = { version = "^2.14.0", optional = true }

38
server/requirements.txt
View File

@ -1,25 +1,36 @@
accelerate==0.20.3 ; python_version >= "3.9" and python_version < "3.13" accelerate==0.20.3 ; python_version >= "3.9" and python_version < "3.13"
aiohttp==3.8.5 ; python_version >= "3.9" and python_version < "3.13"
aiosignal==1.3.1 ; python_version >= "3.9" and python_version < "3.13"
async-timeout==4.0.3 ; python_version >= "3.9" and python_version < "3.13"
attrs==23.1.0 ; python_version >= "3.9" and python_version < "3.13"
backoff==2.2.1 ; python_version >= "3.9" and python_version < "3.13" backoff==2.2.1 ; python_version >= "3.9" and python_version < "3.13"
bitsandbytes==0.41.1 ; python_version >= "3.9" and python_version < "3.13"
certifi==2023.7.22 ; python_version >= "3.9" and python_version < "3.13" certifi==2023.7.22 ; python_version >= "3.9" and python_version < "3.13"
charset-normalizer==3.2.0 ; python_version >= "3.9" and python_version < "3.13" charset-normalizer==3.2.0 ; python_version >= "3.9" and python_version < "3.13"
click==8.1.6 ; python_version >= "3.9" and python_version < "3.13" click==8.1.7 ; python_version >= "3.9" and python_version < "3.13"
colorama==0.4.6 ; python_version >= "3.9" and python_version < "3.13" and (sys_platform == "win32" or platform_system == "Windows") colorama==0.4.6 ; python_version >= "3.9" and python_version < "3.13" and (sys_platform == "win32" or platform_system == "Windows")
datasets==2.14.4 ; python_version >= "3.9" and python_version < "3.13"
deprecated==1.2.14 ; python_version >= "3.9" and python_version < "3.13" deprecated==1.2.14 ; python_version >= "3.9" and python_version < "3.13"
dill==0.3.7 ; python_version >= "3.9" and python_version < "3.13"
einops==0.6.1 ; python_version >= "3.9" and python_version < "3.13" einops==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
filelock==3.12.2 ; python_version >= "3.9" and python_version < "3.13" filelock==3.12.3 ; python_version >= "3.9" and python_version < "3.13"
frozenlist==1.4.0 ; python_version >= "3.9" and python_version < "3.13"
fsspec==2023.6.0 ; python_version >= "3.9" and python_version < "3.13" fsspec==2023.6.0 ; python_version >= "3.9" and python_version < "3.13"
fsspec[http]==2023.6.0 ; python_version >= "3.9" and python_version < "3.13"
googleapis-common-protos==1.60.0 ; python_version >= "3.9" and python_version < "3.13" googleapis-common-protos==1.60.0 ; python_version >= "3.9" and python_version < "3.13"
grpc-interceptor==0.15.2 ; python_version >= "3.9" and python_version < "3.13" grpc-interceptor==0.15.3 ; python_version >= "3.9" and python_version < "3.13"
grpcio-reflection==1.57.0 ; python_version >= "3.9" and python_version < "3.13" grpcio-reflection==1.57.0 ; python_version >= "3.9" and python_version < "3.13"
grpcio-status==1.57.0 ; python_version >= "3.9" and python_version < "3.13" grpcio-status==1.57.0 ; python_version >= "3.9" and python_version < "3.13"
grpcio==1.57.0 ; python_version >= "3.9" and python_version < "3.13" grpcio==1.57.0 ; python_version >= "3.9" and python_version < "3.13"
hf-transfer==0.1.3 ; python_version >= "3.9" and python_version < "3.13" hf-transfer==0.1.3 ; python_version >= "3.9" and python_version < "3.13"
huggingface-hub==0.14.1 ; python_version >= "3.9" and python_version < "3.13" huggingface-hub==0.16.4 ; python_version >= "3.9" and python_version < "3.13"
idna==3.4 ; python_version >= "3.9" and python_version < "3.13" idna==3.4 ; python_version >= "3.9" and python_version < "3.13"
jinja2==3.1.2 ; python_version >= "3.9" and python_version < "3.13" jinja2==3.1.2 ; python_version >= "3.9" and python_version < "3.13"
loguru==0.6.0 ; python_version >= "3.9" and python_version < "3.13" loguru==0.6.0 ; python_version >= "3.9" and python_version < "3.13"
markupsafe==2.1.3 ; python_version >= "3.9" and python_version < "3.13" markupsafe==2.1.3 ; python_version >= "3.9" and python_version < "3.13"
mpmath==1.3.0 ; python_version >= "3.9" and python_version < "3.13" mpmath==1.3.0 ; python_version >= "3.9" and python_version < "3.13"
multidict==6.0.4 ; python_version >= "3.9" and python_version < "3.13"
multiprocess==0.70.15 ; python_version >= "3.9" and python_version < "3.13"
networkx==3.1 ; python_version >= "3.9" and python_version < "3.13" networkx==3.1 ; python_version >= "3.9" and python_version < "3.13"
numpy==1.25.2 ; python_version >= "3.9" and python_version < "3.13" numpy==1.25.2 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-api==1.15.0 ; python_version >= "3.9" and python_version < "3.13" opentelemetry-api==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
@ -32,24 +43,33 @@ opentelemetry-proto==1.15.0 ; python_version >= "3.9" and python_version < "3.13
opentelemetry-sdk==1.15.0 ; python_version >= "3.9" and python_version < "3.13" opentelemetry-sdk==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
opentelemetry-semantic-conventions==0.36b0 ; python_version >= "3.9" and python_version < "3.13" opentelemetry-semantic-conventions==0.36b0 ; python_version >= "3.9" and python_version < "3.13"
packaging==23.1 ; python_version >= "3.9" and python_version < "3.13" packaging==23.1 ; python_version >= "3.9" and python_version < "3.13"
pandas==2.0.3 ; python_version >= "3.9" and python_version < "3.13"
peft==0.4.0 ; python_version >= "3.9" and python_version < "3.13" peft==0.4.0 ; python_version >= "3.9" and python_version < "3.13"
pillow==10.0.0 ; python_version >= "3.9" and python_version < "3.13" pillow==10.0.0 ; python_version >= "3.9" and python_version < "3.13"
protobuf==4.24.0 ; python_version >= "3.9" and python_version < "3.13" protobuf==4.24.2 ; python_version >= "3.9" and python_version < "3.13"
psutil==5.9.5 ; python_version >= "3.9" and python_version < "3.13" psutil==5.9.5 ; python_version >= "3.9" and python_version < "3.13"
pyarrow==13.0.0 ; python_version >= "3.9" and python_version < "3.13"
python-dateutil==2.8.2 ; python_version >= "3.9" and python_version < "3.13"
pytz==2023.3 ; python_version >= "3.9" and python_version < "3.13"
pyyaml==6.0.1 ; python_version >= "3.9" and python_version < "3.13" pyyaml==6.0.1 ; python_version >= "3.9" and python_version < "3.13"
regex==2023.8.8 ; python_version >= "3.9" and python_version < "3.13" regex==2023.8.8 ; python_version >= "3.9" and python_version < "3.13"
requests==2.31.0 ; python_version >= "3.9" and python_version < "3.13" requests==2.31.0 ; python_version >= "3.9" and python_version < "3.13"
safetensors==0.3.2 ; python_version >= "3.9" and python_version < "3.13" safetensors==0.3.3 ; python_version >= "3.9" and python_version < "3.13"
scipy==1.11.1 ; python_version >= "3.9" and python_version < "3.13" scipy==1.11.2 ; python_version >= "3.9" and python_version < "3.13"
sentencepiece==0.1.99 ; python_version >= "3.9" and python_version < "3.13" sentencepiece==0.1.99 ; python_version >= "3.9" and python_version < "3.13"
setuptools==68.0.0 ; python_version >= "3.9" and python_version < "3.13" setuptools==68.1.2 ; python_version >= "3.9" and python_version < "3.13"
six==1.16.0 ; python_version >= "3.9" and python_version < "3.13"
sympy==1.12 ; python_version >= "3.9" and python_version < "3.13" sympy==1.12 ; python_version >= "3.9" and python_version < "3.13"
texttable==1.6.7 ; python_version >= "3.9" and python_version < "3.13"
tokenizers==0.13.3 ; python_version >= "3.9" and python_version < "3.13" tokenizers==0.13.3 ; python_version >= "3.9" and python_version < "3.13"
torch==2.0.1 ; python_version >= "3.9" and python_version < "3.13" torch==2.0.1 ; python_version >= "3.9" and python_version < "3.13"
tqdm==4.66.1 ; python_version >= "3.9" and python_version < "3.13" tqdm==4.66.1 ; python_version >= "3.9" and python_version < "3.13"
transformers==4.31.0 ; python_version >= "3.9" and python_version < "3.13" transformers==4.32.1 ; python_version >= "3.9" and python_version < "3.13"
typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13" typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13"
typing-extensions==4.7.1 ; python_version >= "3.9" and python_version < "3.13" typing-extensions==4.7.1 ; python_version >= "3.9" and python_version < "3.13"
tzdata==2023.3 ; python_version >= "3.9" and python_version < "3.13"
urllib3==2.0.4 ; python_version >= "3.9" and python_version < "3.13" urllib3==2.0.4 ; python_version >= "3.9" and python_version < "3.13"
win32-setctime==1.1.0 ; python_version >= "3.9" and python_version < "3.13" and sys_platform == "win32" win32-setctime==1.1.0 ; python_version >= "3.9" and python_version < "3.13" and sys_platform == "win32"
wrapt==1.15.0 ; python_version >= "3.9" and python_version < "3.13" wrapt==1.15.0 ; python_version >= "3.9" and python_version < "3.13"
xxhash==3.3.0 ; python_version >= "3.9" and python_version < "3.13"
yarl==1.9.2 ; python_version >= "3.9" and python_version < "3.13"

21
server/tests/utils/test_tokens.py
View File

@ -1,7 +1,9 @@
import torch
from text_generation_server.utils.tokens import ( from text_generation_server.utils.tokens import (
StopSequenceCriteria, StopSequenceCriteria,
StoppingCriteria, StoppingCriteria,
FinishReason, FinishReason,
batch_top_tokens,
) )
@ -42,3 +44,22 @@ def test_stopping_criteria_max():
assert criteria(1, "") == (False, None) assert criteria(1, "") == (False, None)
assert criteria(1, "") == (False, None) assert criteria(1, "") == (False, None)
assert criteria(1, "") == (True, FinishReason.FINISH_REASON_LENGTH) assert criteria(1, "") == (True, FinishReason.FINISH_REASON_LENGTH)
def test_batch_top_tokens():
top_n_tokens = [0, 2, 3, 4, 5]
top_n_tokens_tensor = torch.tensor(top_n_tokens)
inp_logprobs = torch.tensor([[-1., -3., -4., -2., -3.]] * 5)
topn_tok_ids, topn_tok_logprobs = batch_top_tokens(top_n_tokens, top_n_tokens_tensor, inp_logprobs)
assert topn_tok_ids[0] == []
assert topn_tok_ids[1] == [0, 3]
assert topn_tok_ids[2] == [0, 3, 1, 4]
assert topn_tok_ids[3] == [0, 3, 1, 4]
assert topn_tok_ids[4] == [0, 3, 1, 4, 2]
assert topn_tok_logprobs[0] == []
assert topn_tok_logprobs[1] == [-1, -2]
assert topn_tok_logprobs[2] == [-1, -2, -3, -3]
assert topn_tok_logprobs[3] == [-1, -2, -3, -3]
assert topn_tok_logprobs[4] == [-1, -2, -3, -3, -4]

3
server/text_generation_server/cli.py
View File

@ -125,6 +125,9 @@ def download_weights(
try: try:
adapter_config_filename = hf_hub_download(model_id, revision=revision, filename="adapter_config.json") adapter_config_filename = hf_hub_download(model_id, revision=revision, filename="adapter_config.json")
utils.download_and_unload_peft(model_id, revision, trust_remote_code=trust_remote_code) utils.download_and_unload_peft(model_id, revision, trust_remote_code=trust_remote_code)
is_local_model = True
utils.weight_files(model_id, revision, extension)
return
except (utils.LocalEntryNotFoundError, utils.EntryNotFoundError): except (utils.LocalEntryNotFoundError, utils.EntryNotFoundError):
pass pass

58
server/text_generation_server/models/causal_lm.py
View File

@ -1,3 +1,4 @@
from text_generation_server.utils.tokens import batch_top_tokens
import torch import torch
import inspect import inspect
@ -12,6 +13,7 @@ from text_generation_server.models.types import (
PrefillTokens, PrefillTokens,
Generation, Generation,
GeneratedText, GeneratedText,
TopTokens,
) )
from text_generation_server.pb import generate_pb2 from text_generation_server.pb import generate_pb2
from text_generation_server.utils import NextTokenChooser, StoppingCriteria, Sampling from text_generation_server.utils import NextTokenChooser, StoppingCriteria, Sampling
@ -42,6 +44,8 @@ class CausalLMBatch(Batch):
# Generation helpers # Generation helpers
next_token_choosers: List[NextTokenChooser] next_token_choosers: List[NextTokenChooser]
stopping_criterias: List[StoppingCriteria] stopping_criterias: List[StoppingCriteria]
top_n_tokens: List[int]
top_n_tokens_tensor: torch.Tensor
# Metadata used for padding # Metadata used for padding
max_input_length: int max_input_length: int
@ -72,6 +76,7 @@ class CausalLMBatch(Batch):
inputs = [] inputs = []
next_token_choosers = [] next_token_choosers = []
stopping_criterias = [] stopping_criterias = []
top_n_tokens = []
prefix_offsets = [] prefix_offsets = []
read_offsets = [] read_offsets = []
requests_idx_mapping = {} requests_idx_mapping = {}
@ -88,6 +93,7 @@ class CausalLMBatch(Batch):
r.stopping_parameters, tokenizer r.stopping_parameters, tokenizer
) )
stopping_criterias.append(stopping_criteria) stopping_criterias.append(stopping_criteria)
top_n_tokens.append(r.top_n_tokens)
max_truncation = max(max_truncation, r.truncate) max_truncation = max(max_truncation, r.truncate)
max_decode_tokens += stopping_criteria.max_new_tokens max_decode_tokens += stopping_criteria.max_new_tokens
padding_right_offset = max( padding_right_offset = max(
@ -121,6 +127,9 @@ class CausalLMBatch(Batch):
position_ids = tokenized_inputs["attention_mask"].long().cumsum(-1) - 1 position_ids = tokenized_inputs["attention_mask"].long().cumsum(-1) - 1
position_ids.masked_fill_(tokenized_inputs["attention_mask"] == 0, 1) position_ids.masked_fill_(tokenized_inputs["attention_mask"] == 0, 1)
all_input_ids = tokenized_inputs["input_ids"].T.split(1, dim=1) all_input_ids = tokenized_inputs["input_ids"].T.split(1, dim=1)
top_n_tokens_tensor = torch.tensor(
top_n_tokens, device=device, dtype=torch.int64
)
max_tokens = len(inputs) * (max_input_length + max_decode_tokens) max_tokens = len(inputs) * (max_input_length + max_decode_tokens)
@ -138,6 +147,8 @@ class CausalLMBatch(Batch):
read_offsets=read_offsets, read_offsets=read_offsets,
next_token_choosers=next_token_choosers, next_token_choosers=next_token_choosers,
stopping_criterias=stopping_criterias, stopping_criterias=stopping_criterias,
top_n_tokens=top_n_tokens,
top_n_tokens_tensor=top_n_tokens_tensor,
max_input_length=max_input_length.item(), max_input_length=max_input_length.item(),
padding_right_offset=padding_right_offset, padding_right_offset=padding_right_offset,
max_tokens=max_tokens, max_tokens=max_tokens,
@ -163,6 +174,7 @@ class CausalLMBatch(Batch):
next_token_choosers = [] next_token_choosers = []
stopping_criterias = [] stopping_criterias = []
top_n_tokens = []
total_remaining_decode_tokens = 0 total_remaining_decode_tokens = 0
new_padding_right_offset = 0 new_padding_right_offset = 0
@ -184,6 +196,7 @@ class CausalLMBatch(Batch):
next_token_choosers.append(self.next_token_choosers[idx]) next_token_choosers.append(self.next_token_choosers[idx])
stopping_criteria = self.stopping_criterias[idx] stopping_criteria = self.stopping_criterias[idx]
stopping_criterias.append(stopping_criteria) stopping_criterias.append(stopping_criteria)
top_n_tokens.append(self.top_n_tokens[idx])
remaining_decode_tokens = ( remaining_decode_tokens = (
stopping_criteria.max_new_tokens - stopping_criteria.current_tokens stopping_criteria.max_new_tokens - stopping_criteria.current_tokens
) )
@ -223,6 +236,7 @@ class CausalLMBatch(Batch):
layer[1] = past_values[keep_indices, :, -past_kv_length:, :] layer[1] = past_values[keep_indices, :, -past_kv_length:, :]
del past_values del past_values
top_n_tokens_tensor = self.top_n_tokens_tensor[keep_indices]
max_tokens = len(request_ids) * max_input_length + total_remaining_decode_tokens max_tokens = len(request_ids) * max_input_length + total_remaining_decode_tokens
self.requests = requests self.requests = requests
@ -235,6 +249,8 @@ class CausalLMBatch(Batch):
self.read_offsets = read_offsets self.read_offsets = read_offsets
self.next_token_choosers = next_token_choosers self.next_token_choosers = next_token_choosers
self.stopping_criterias = stopping_criterias self.stopping_criterias = stopping_criterias
self.top_n_tokens = top_n_tokens
self.top_n_tokens_tensor = top_n_tokens_tensor
self.max_input_length = max_input_length self.max_input_length = max_input_length
self.padding_right_offset = new_padding_right_offset self.padding_right_offset = new_padding_right_offset
self.max_tokens = max_tokens self.max_tokens = max_tokens
@ -262,6 +278,7 @@ class CausalLMBatch(Batch):
all_input_ids = [] all_input_ids = []
next_token_choosers = [] next_token_choosers = []
stopping_criterias = [] stopping_criterias = []
top_n_tokens = []
max_tokens = 0 max_tokens = 0
# Batch tensors # Batch tensors
@ -269,6 +286,7 @@ class CausalLMBatch(Batch):
attention_mask = None attention_mask = None
position_ids = None position_ids = None
past_key_values = [] past_key_values = []
top_n_tokens_tensor = None
# Used for slicing correctly inside the tensors # Used for slicing correctly inside the tensors
# Equivalent to a cumsum on batch sizes # Equivalent to a cumsum on batch sizes
@ -281,6 +299,7 @@ class CausalLMBatch(Batch):
all_input_ids.extend(batch.all_input_ids) all_input_ids.extend(batch.all_input_ids)
next_token_choosers.extend(batch.next_token_choosers) next_token_choosers.extend(batch.next_token_choosers)
stopping_criterias.extend(batch.stopping_criterias) stopping_criterias.extend(batch.stopping_criterias)
top_n_tokens.extend(batch.top_n_tokens)
if i == 0: if i == 0:
requests_idx_mapping = batch.requests_idx_mapping requests_idx_mapping = batch.requests_idx_mapping
@ -310,6 +329,12 @@ class CausalLMBatch(Batch):
(total_batch_size, max_input_length + padding_right_offset), (total_batch_size, max_input_length + padding_right_offset),
) )
if top_n_tokens_tensor is None:
top_n_tokens_tensor = batches[0].top_n_tokens_tensor.new_zeros(
total_batch_size,
)
top_n_tokens_tensor[start_index:end_index] = batch.top_n_tokens_tensor
# We need to slice the attention mask to remove padding from previous steps # We need to slice the attention mask to remove padding from previous steps
# and to remove unused allocated space # and to remove unused allocated space
left_offset = max_input_length - batch.max_input_length left_offset = max_input_length - batch.max_input_length
@ -438,6 +463,8 @@ class CausalLMBatch(Batch):
read_offsets=read_offsets, read_offsets=read_offsets,
next_token_choosers=next_token_choosers, next_token_choosers=next_token_choosers,
stopping_criterias=stopping_criterias, stopping_criterias=stopping_criterias,
top_n_tokens=top_n_tokens,
top_n_tokens_tensor=top_n_tokens_tensor,
max_input_length=max_input_length, max_input_length=max_input_length,
padding_right_offset=padding_right_offset, padding_right_offset=padding_right_offset,
keys_head_dim_last=batches[0].keys_head_dim_last, keys_head_dim_last=batches[0].keys_head_dim_last,
@ -549,6 +576,12 @@ class CausalLM(Model):
generations: List[Generation] = [] generations: List[Generation] = []
stopped = True stopped = True
batch_top_token_ids, batch_top_token_logprobs = batch_top_tokens(
batch.top_n_tokens,
batch.top_n_tokens_tensor,
torch.softmax(logits[:, -1], -1),
)
# Zipped iterator # Zipped iterator
iterator = zip( iterator = zip(
batch.requests, batch.requests,
@ -559,6 +592,9 @@ class CausalLM(Model):
batch.next_token_choosers, batch.next_token_choosers,
batch.stopping_criterias, batch.stopping_criterias,
batch.all_input_ids, batch.all_input_ids,
batch.top_n_tokens,
batch_top_token_ids,
batch_top_token_logprobs,
) )
# For each member of the batch # For each member of the batch
@ -571,6 +607,9 @@ class CausalLM(Model):
next_token_chooser, next_token_chooser,
stopping_criteria, stopping_criteria,
all_input_ids, all_input_ids,
top_n_tokens,
top_token_ids,
top_token_logprobs,
) in enumerate(iterator): ) in enumerate(iterator):
# Select next token # Select next token
next_token_id, logprobs = next_token_chooser( next_token_id, logprobs = next_token_chooser(
@ -637,6 +676,24 @@ class CausalLM(Model):
else: else:
prefill_tokens = None prefill_tokens = None
if top_n_tokens > 0:
toptoken_texts = self.tokenizer.batch_decode(
top_token_ids,
clean_up_tokenization_spaces=False,
skip_special_tokens=False,
)
special_toptokens = [
token_id in self.all_special_ids for token_id in top_token_ids
]
top_tokens = TopTokens(
top_token_ids,
top_token_logprobs,
toptoken_texts,
special_toptokens,
)
else:
top_tokens = None
generation = Generation( generation = Generation(
request.id, request.id,
prefill_tokens, prefill_tokens,
@ -645,6 +702,7 @@ class CausalLM(Model):
next_token_text, next_token_text,
next_token_id_squeezed.item() in self.all_special_ids, next_token_id_squeezed.item() in self.all_special_ids,
generated_text, generated_text,
top_tokens,
) )
generations.append(generation) generations.append(generation)

4
server/text_generation_server/models/custom_modeling/flash_llama_modeling.py
View File

@ -64,6 +64,7 @@ class LlamaConfig(PretrainedConfig):
pretraining_tp=1, pretraining_tp=1,
tie_word_embeddings=False, tie_word_embeddings=False,
rope_scaling=None, rope_scaling=None,
rope_theta=10000.0,
**kwargs, **kwargs,
): ):
self.vocab_size = vocab_size self.vocab_size = vocab_size
@ -84,6 +85,7 @@ class LlamaConfig(PretrainedConfig):
self.pretraining_tp = pretraining_tp self.pretraining_tp = pretraining_tp
self.use_cache = use_cache self.use_cache = use_cache
self.rope_scaling = rope_scaling self.rope_scaling = rope_scaling
self.rope_theta = rope_theta
super().__init__( super().__init__(
pad_token_id=pad_token_id, pad_token_id=pad_token_id,
@ -189,7 +191,7 @@ class FlashLlamaAttention(torch.nn.Module):
# config=config, prefix=f"{prefix}.rotary_emb", weights=weights # config=config, prefix=f"{prefix}.rotary_emb", weights=weights
# ) # )
self.rotary_emb = PositionRotaryEmbedding.static( self.rotary_emb = PositionRotaryEmbedding.static(
config=config, dim=self.head_size, base=10000.0, device=weights.device config=config, dim=self.head_size, base=config.rope_theta, device=weights.device
) )
self.softmax_scale = self.head_size**-0.5 self.softmax_scale = self.head_size**-0.5

9
server/text_generation_server/models/custom_modeling/flash_rw_modeling.py
View File

@ -241,19 +241,21 @@ class FlashRWLargeAttention(torch.nn.Module):
hidden_size = config.hidden_size hidden_size = config.hidden_size
num_heads = config.n_head num_heads = config.n_head
num_heads_kv = config.n_head_kv # num_heads_kv = config.n_head_kv
num_groups = config.n_head_kv
self.hidden_size = hidden_size self.hidden_size = hidden_size
self.head_size = hidden_size // num_heads self.head_size = hidden_size // num_heads
self.num_groups = num_groups
self.rotary_emb = PositionRotaryEmbedding.static( self.rotary_emb = PositionRotaryEmbedding.static(
config=config, dim=self.head_size, base=10000.0, device=weights.device config=config, dim=self.head_size, base=10000.0, device=weights.device
) )
self.softmax_scale = self.head_size ** (-0.5) self.softmax_scale = self.head_size ** (-0.5)
self.num_groups = num_heads // (num_heads_kv * 2) # self.num_groups = num_heads // (num_heads_kv * 2)
self.num_heads = num_heads // self.num_groups self.num_heads = num_heads // self.num_groups
self.num_heads_kv = num_heads_kv // self.num_groups # self.num_heads_kv = num_heads_kv // self.num_groups
process_group = weights.process_group process_group = weights.process_group
if process_group.size() > self.num_groups: if process_group.size() > self.num_groups:
@ -264,6 +266,7 @@ class FlashRWLargeAttention(torch.nn.Module):
raise NotImplementedError( raise NotImplementedError(
f"Tensor Parallelism is not implemented for {self.num_groups} not divisible by {process_group.size()}" f"Tensor Parallelism is not implemented for {self.num_groups} not divisible by {process_group.size()}"
) )
self.num_groups = self.num_groups // process_group.size() self.num_groups = self.num_groups // process_group.size()
self.query_key_value = TensorParallelColumnLinear.load( self.query_key_value = TensorParallelColumnLinear.load(

4
server/text_generation_server/models/custom_modeling/idefics_config.py
View File

@ -51,7 +51,7 @@ class IdeficsVisionConfig(PretrainedConfig):
Number of attention heads for each attention layer in the Transformer encoder. Number of attention heads for each attention layer in the Transformer encoder.
image_num_channels (`int`, *optional*, defaults to `3`): image_num_channels (`int`, *optional*, defaults to `3`):
Number of image channels. Number of image channels.
hidden_act (`str` or `function`, *optional*, defaults to `"quick_gelu"`): hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`, The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
`"relu"`, `"selu"` and `"gelu_new"` ``"quick_gelu"` are supported. `"relu"`, `"selu"` and `"gelu_new"` ``"quick_gelu"` are supported.
layer_norm_eps (`float`, *optional*, defaults to 1e-5): layer_norm_eps (`float`, *optional*, defaults to 1e-5):
@ -80,7 +80,7 @@ class IdeficsVisionConfig(PretrainedConfig):
num_hidden_layers=32, num_hidden_layers=32,
num_attention_heads=16, num_attention_heads=16,
num_channels=3, num_channels=3,
hidden_act="quick_gelu", hidden_act="gelu",
layer_norm_eps=1e-5, layer_norm_eps=1e-5,
attention_dropout=0.0, attention_dropout=0.0,
initializer_range=0.02, initializer_range=0.02,

57
server/text_generation_server/models/flash_causal_lm.py
View File

@ -1,5 +1,6 @@
import math import math
import itertools import itertools
from text_generation_server.utils.tokens import batch_top_tokens
import torch import torch
import torch.distributed import torch.distributed
@ -16,6 +17,7 @@ from text_generation_server.models.types import (
PrefillTokens, PrefillTokens,
Generation, Generation,
GeneratedText, GeneratedText,
TopTokens,
) )
from text_generation_server.pb import generate_pb2 from text_generation_server.pb import generate_pb2
from text_generation_server.utils import StoppingCriteria, HeterogeneousNextTokenChooser from text_generation_server.utils import StoppingCriteria, HeterogeneousNextTokenChooser
@ -165,6 +167,8 @@ class FlashCausalLMBatch(Batch):
# Generation helpers # Generation helpers
next_token_chooser: HeterogeneousNextTokenChooser next_token_chooser: HeterogeneousNextTokenChooser
stopping_criterias: List[StoppingCriteria] stopping_criterias: List[StoppingCriteria]
top_n_tokens: List[int]
top_n_tokens_tensor: torch.Tensor
# Number of blocks in this batch # Number of blocks in this batch
blocks: int blocks: int
@ -217,6 +221,7 @@ class FlashCausalLMBatch(Batch):
next_token_chooser_parameters = [] next_token_chooser_parameters = []
stopping_criterias = [] stopping_criterias = []
top_n_tokens = []
# Cumulative length # Cumulative length
cumulative_length = 0 cumulative_length = 0
@ -259,6 +264,7 @@ class FlashCausalLMBatch(Batch):
) )
max_new_tokens = stopping_criteria.max_new_tokens max_new_tokens = stopping_criteria.max_new_tokens
stopping_criterias.append(stopping_criteria) stopping_criterias.append(stopping_criteria)
top_n_tokens.append(r.top_n_tokens)
# Paged attention # Paged attention
# Remove one as the first token des not have a past # Remove one as the first token des not have a past
@ -352,6 +358,9 @@ class FlashCausalLMBatch(Batch):
prefill_next_token_indices = torch.tensor( prefill_next_token_indices = torch.tensor(
prefill_next_token_indices, dtype=torch.int64, device=device prefill_next_token_indices, dtype=torch.int64, device=device
) )
top_n_tokens_tensor = torch.tensor(
top_n_tokens, device=device, dtype=torch.int64
)
return cls( return cls(
batch_id=pb.id, batch_id=pb.id,
@ -378,6 +387,8 @@ class FlashCausalLMBatch(Batch):
all_input_ids_tensor=all_input_ids_tensor, all_input_ids_tensor=all_input_ids_tensor,
next_token_chooser=next_token_chooser, next_token_chooser=next_token_chooser,
stopping_criterias=stopping_criterias, stopping_criterias=stopping_criterias,
top_n_tokens=top_n_tokens,
top_n_tokens_tensor=top_n_tokens_tensor,
blocks=blocks, blocks=blocks,
max_blocks=max_blocks, max_blocks=max_blocks,
) )
@ -417,6 +428,7 @@ class FlashCausalLMBatch(Batch):
read_offsets = [] read_offsets = []
stopping_criterias = [] stopping_criterias = []
top_n_tokens = []
blocks = 0 blocks = 0
max_blocks = 0 max_blocks = 0
@ -443,6 +455,8 @@ class FlashCausalLMBatch(Batch):
stopping_criteria = self.stopping_criterias[idx] stopping_criteria = self.stopping_criterias[idx]
stopping_criterias.append(stopping_criteria) stopping_criterias.append(stopping_criteria)
top_n_tokens.append(self.top_n_tokens[idx])
remaining_tokens = ( remaining_tokens = (
stopping_criteria.max_new_tokens - stopping_criteria.current_tokens stopping_criteria.max_new_tokens - stopping_criteria.current_tokens
) )
@ -487,6 +501,7 @@ class FlashCausalLMBatch(Batch):
input_lengths_tensor = self.input_lengths_tensor[indices] input_lengths_tensor = self.input_lengths_tensor[indices]
slots = self.slots[slot_filtering_indices] slots = self.slots[slot_filtering_indices]
next_token_chooser = self.next_token_chooser.filter(indices) next_token_chooser = self.next_token_chooser.filter(indices)
top_n_tokens_tensor = self.top_n_tokens_tensor[indices]
start_slots = torch.tensor(start_slots, dtype=torch.int64) start_slots = torch.tensor(start_slots, dtype=torch.int64)
@ -518,6 +533,8 @@ class FlashCausalLMBatch(Batch):
all_input_ids_tensor=all_input_ids_tensor, all_input_ids_tensor=all_input_ids_tensor,
next_token_chooser=next_token_chooser, next_token_chooser=next_token_chooser,
stopping_criterias=stopping_criterias, stopping_criterias=stopping_criterias,
top_n_tokens=top_n_tokens,
top_n_tokens_tensor=top_n_tokens_tensor,
blocks=blocks, blocks=blocks,
max_blocks=max_blocks, max_blocks=max_blocks,
) )
@ -566,6 +583,9 @@ class FlashCausalLMBatch(Batch):
all_input_ids_tensor = batches[0].all_input_ids_tensor.new_zeros( all_input_ids_tensor = batches[0].all_input_ids_tensor.new_zeros(
(total_batch_size, max_length) (total_batch_size, max_length)
) )
top_n_tokens_tensor = batches[0].top_n_tokens_tensor.new_zeros(
total_batch_size,
)
start_slots = [] start_slots = []
block_tables = [] block_tables = []
@ -577,6 +597,7 @@ class FlashCausalLMBatch(Batch):
next_token_chooser_parameters = [] next_token_chooser_parameters = []
stopping_criterias = [] stopping_criterias = []
top_n_tokens = []
# Cumulative length # Cumulative length
cumulative_batch_size = 0 cumulative_batch_size = 0
@ -602,6 +623,7 @@ class FlashCausalLMBatch(Batch):
position_ids[start_index:end_index] = batch.position_ids position_ids[start_index:end_index] = batch.position_ids
slot_indices[start_index:end_index] = batch.slot_indices + cumulative_slots slot_indices[start_index:end_index] = batch.slot_indices + cumulative_slots
input_lengths_tensor[start_index:end_index] = batch.input_lengths_tensor input_lengths_tensor[start_index:end_index] = batch.input_lengths_tensor
top_n_tokens_tensor[start_index:end_index] = batch.top_n_tokens_tensor
slots[slots_start_index:slots_end_index] = batch.slots slots[slots_start_index:slots_end_index] = batch.slots
all_input_ids_tensor[ all_input_ids_tensor[
@ -624,6 +646,8 @@ class FlashCausalLMBatch(Batch):
next_token_chooser_parameters.extend([r.parameters for r in batch.requests]) next_token_chooser_parameters.extend([r.parameters for r in batch.requests])
stopping_criterias.extend(batch.stopping_criterias) stopping_criterias.extend(batch.stopping_criterias)
top_n_tokens.extend(batch.top_n_tokens)
# Update # Update
cumulative_batch_size += len(batch) cumulative_batch_size += len(batch)
cumulative_slots += len(batch.slots) cumulative_slots += len(batch.slots)
@ -666,6 +690,8 @@ class FlashCausalLMBatch(Batch):
all_input_ids_tensor=all_input_ids_tensor, all_input_ids_tensor=all_input_ids_tensor,
next_token_chooser=next_token_chooser, next_token_chooser=next_token_chooser,
stopping_criterias=stopping_criterias, stopping_criterias=stopping_criterias,
top_n_tokens=top_n_tokens,
top_n_tokens_tensor=top_n_tokens_tensor,
blocks=blocks, blocks=blocks,
max_blocks=max_blocks, max_blocks=max_blocks,
) )
@ -831,10 +857,14 @@ class FlashCausalLM(Model):
else: else:
next_token_logits = out next_token_logits = out
next_input_ids, next_token_logprobs = batch.next_token_chooser( next_input_ids, next_token_logprobs, logprobs = batch.next_token_chooser(
batch.all_input_ids_tensor[:, : batch.max_seqlen], next_token_logits batch.all_input_ids_tensor[:, : batch.max_seqlen], next_token_logits
) )
batch_top_token_ids, batch_top_token_logprobs = batch_top_tokens(
batch.top_n_tokens, batch.top_n_tokens_tensor, logprobs
)
if prefill: if prefill:
if len(batch) > 1 and prefill_logprobs: if len(batch) > 1 and prefill_logprobs:
# We create the prefill_tokens_indices tensor that will be used to gather prefill logprobs # We create the prefill_tokens_indices tensor that will be used to gather prefill logprobs
@ -931,8 +961,11 @@ class FlashCausalLM(Model):
batch.all_input_ids, batch.all_input_ids,
batch.next_token_chooser.do_sample, batch.next_token_chooser.do_sample,
batch.next_token_chooser.seeds, batch.next_token_chooser.seeds,
batch.top_n_tokens,
next_token_ids, next_token_ids,
next_token_logprobs, next_token_logprobs,
batch_top_token_ids,
batch_top_token_logprobs,
) )
# For each member of the batch # For each member of the batch
@ -945,8 +978,11 @@ class FlashCausalLM(Model):
all_input_ids, all_input_ids,
do_sample, do_sample,
seed, seed,
top_n_tokens,
next_token_id, next_token_id,
next_token_logprob, next_token_logprob,
top_token_ids,
top_token_logprobs,
) in enumerate(iterator): ) in enumerate(iterator):
# Append next token to all tokens # Append next token to all tokens
all_input_ids.append(next_token_id) all_input_ids.append(next_token_id)
@ -1005,6 +1041,24 @@ class FlashCausalLM(Model):
else: else:
prefill_tokens = None prefill_tokens = None
if top_n_tokens > 0:
toptoken_texts = self.tokenizer.batch_decode(
top_token_ids,
clean_up_tokenization_spaces=False,
skip_special_tokens=False,
)
special_toptokens = [
token_id in self.all_special_ids for token_id in top_token_ids
]
top_tokens = TopTokens(
top_token_ids,
top_token_logprobs,
toptoken_texts,
special_toptokens,
)
else:
top_tokens = None
generation = Generation( generation = Generation(
request.id, request.id,
prefill_tokens, prefill_tokens,
@ -1013,6 +1067,7 @@ class FlashCausalLM(Model):
next_token_text, next_token_text,
next_token_id in self.all_special_ids, next_token_id in self.all_special_ids,
generated_text, generated_text,
top_tokens,
) )
generations.append(generation) generations.append(generation)

5
server/text_generation_server/models/flash_rw.py
View File

@ -54,7 +54,10 @@ class FlashRWSharded(FlashCausalLM):
device, device,
dtype, dtype,
process_group=self.process_group, process_group=self.process_group,
aliases={"lm_head.weight": ["transformer.word_embeddings.weight"]}, aliases={
"lm_head.weight": ["transformer.word_embeddings.weight"],
"transformer.word_embeddings.weight": ["lm_head.weight"],
},
) )
config.quantize = quantize config.quantize = quantize

3
server/text_generation_server/models/idefics_causal_lm.py
View File

@ -763,6 +763,8 @@ class IdeficsCausalLM(Model):
else: else:
prefill_tokens = None prefill_tokens = None
top_tokens=None
generation = Generation( generation = Generation(
request.id, request.id,
prefill_tokens, prefill_tokens,
@ -771,6 +773,7 @@ class IdeficsCausalLM(Model):
next_token_text, next_token_text,
next_token_id_squeezed.item() in self.all_special_ids, next_token_id_squeezed.item() in self.all_special_ids,
generated_text, generated_text,
top_tokens
) )
generations.append(generation) generations.append(generation)

59
server/text_generation_server/models/seq2seq_lm.py
View File

@ -1,3 +1,4 @@
from text_generation_server.utils.tokens import batch_top_tokens
import torch import torch
from dataclasses import dataclass from dataclasses import dataclass
@ -11,6 +12,7 @@ from text_generation_server.models.types import (
Batch, Batch,
Generation, Generation,
PrefillTokens, PrefillTokens,
TopTokens,
) )
from text_generation_server.pb import generate_pb2 from text_generation_server.pb import generate_pb2
from text_generation_server.utils import NextTokenChooser, StoppingCriteria, Sampling from text_generation_server.utils import NextTokenChooser, StoppingCriteria, Sampling
@ -48,6 +50,8 @@ class Seq2SeqLMBatch(Batch):
# Generation helpers # Generation helpers
next_token_choosers: List[NextTokenChooser] next_token_choosers: List[NextTokenChooser]
stopping_criterias: List[StoppingCriteria] stopping_criterias: List[StoppingCriteria]
top_n_tokens: List[int]
top_n_tokens_tensor: torch.Tensor
# Metadata used for padding # Metadata used for padding
max_input_length: int max_input_length: int
@ -78,7 +82,7 @@ class Seq2SeqLMBatch(Batch):
inputs = [] inputs = []
next_token_choosers = [] next_token_choosers = []
stopping_criterias = [] stopping_criterias = []
top_n_tokens = []
decoder_input_lengths = [] decoder_input_lengths = []
prefix_offsets = [] prefix_offsets = []
read_offsets = [] read_offsets = []
@ -97,6 +101,7 @@ class Seq2SeqLMBatch(Batch):
r.stopping_parameters, tokenizer r.stopping_parameters, tokenizer
) )
stopping_criterias.append(stopping_criteria) stopping_criterias.append(stopping_criteria)
top_n_tokens.append(r.top_n_tokens)
max_truncation = max(max_truncation, r.truncate) max_truncation = max(max_truncation, r.truncate)
max_decode_tokens += stopping_criteria.max_new_tokens max_decode_tokens += stopping_criteria.max_new_tokens
padding_right_offset = max( padding_right_offset = max(
@ -126,6 +131,9 @@ class Seq2SeqLMBatch(Batch):
prefix_offsets.append(0) prefix_offsets.append(0)
read_offsets.append(1) read_offsets.append(1)
all_decoder_input_ids = decoder_input_ids.view(-1).split(1) all_decoder_input_ids = decoder_input_ids.view(-1).split(1)
top_n_tokens_tensor = torch.tensor(
top_n_tokens, device=device, dtype=torch.int64
)
max_tokens = len(inputs) * (max_input_length + max_decode_tokens) max_tokens = len(inputs) * (max_input_length + max_decode_tokens)
@ -146,6 +154,8 @@ class Seq2SeqLMBatch(Batch):
read_offsets=read_offsets, read_offsets=read_offsets,
next_token_choosers=next_token_choosers, next_token_choosers=next_token_choosers,
stopping_criterias=stopping_criterias, stopping_criterias=stopping_criterias,
top_n_tokens=top_n_tokens,
top_n_tokens_tensor=top_n_tokens_tensor,
max_input_length=max_input_length.item(), max_input_length=max_input_length.item(),
max_decoder_input_length=1, max_decoder_input_length=1,
padding_right_offset=padding_right_offset, padding_right_offset=padding_right_offset,
@ -173,6 +183,7 @@ class Seq2SeqLMBatch(Batch):
next_token_choosers = [] next_token_choosers = []
stopping_criterias = [] stopping_criterias = []
top_n_tokens = []
max_input_length = 0 max_input_length = 0
max_decoder_input_length = 0 max_decoder_input_length = 0
@ -204,6 +215,7 @@ class Seq2SeqLMBatch(Batch):
next_token_choosers.append(self.next_token_choosers[idx]) next_token_choosers.append(self.next_token_choosers[idx])
stopping_criteria = self.stopping_criterias[idx] stopping_criteria = self.stopping_criterias[idx]
stopping_criterias.append(stopping_criteria) stopping_criterias.append(stopping_criteria)
top_n_tokens.append(self.top_n_tokens[idx])
remaining_decode_tokens = ( remaining_decode_tokens = (
stopping_criteria.max_new_tokens - stopping_criteria.current_tokens stopping_criteria.max_new_tokens - stopping_criteria.current_tokens
) )
@ -239,6 +251,7 @@ class Seq2SeqLMBatch(Batch):
layer[2] = layer[2][keep_indices, :, -max_input_length:] layer[2] = layer[2][keep_indices, :, -max_input_length:]
layer[3] = layer[3][keep_indices, :, -max_input_length:] layer[3] = layer[3][keep_indices, :, -max_input_length:]
top_n_tokens_tensor = self.top_n_tokens_tensor[keep_indices]
max_tokens = ( max_tokens = (
len(request_ids) * (max_input_length + max_decoder_input_length) len(request_ids) * (max_input_length + max_decoder_input_length)
+ remaining_decode_tokens + remaining_decode_tokens
@ -254,6 +267,8 @@ class Seq2SeqLMBatch(Batch):
self.read_offsets = read_offsets self.read_offsets = read_offsets
self.next_token_choosers = next_token_choosers self.next_token_choosers = next_token_choosers
self.stopping_criterias = stopping_criterias self.stopping_criterias = stopping_criterias
self.top_n_tokens = top_n_tokens
self.top_n_tokens_tensor = top_n_tokens_tensor
self.max_input_length = max_input_length self.max_input_length = max_input_length
self.max_decoder_input_length = max_decoder_input_length self.max_decoder_input_length = max_decoder_input_length
self.padding_right_offset = padding_right_offset self.padding_right_offset = padding_right_offset
@ -289,6 +304,7 @@ class Seq2SeqLMBatch(Batch):
read_offsets = [] read_offsets = []
next_token_choosers = [] next_token_choosers = []
stopping_criterias = [] stopping_criterias = []
top_n_tokens = []
max_tokens = 0 max_tokens = 0
# Batch tensors # Batch tensors
@ -296,6 +312,7 @@ class Seq2SeqLMBatch(Batch):
decoder_input_ids = None decoder_input_ids = None
decoder_attention_mask = None decoder_attention_mask = None
encoder_last_hidden_state = None encoder_last_hidden_state = None
top_n_tokens_tensor = None
past_key_values = [] past_key_values = []
# Used for slicing correctly inside the tensors # Used for slicing correctly inside the tensors
@ -312,6 +329,7 @@ class Seq2SeqLMBatch(Batch):
read_offsets.extend(batch.read_offsets) read_offsets.extend(batch.read_offsets)
next_token_choosers.extend(batch.next_token_choosers) next_token_choosers.extend(batch.next_token_choosers)
stopping_criterias.extend(batch.stopping_criterias) stopping_criterias.extend(batch.stopping_criterias)
top_n_tokens.extend(batch.top_n_tokens)
if i == 0: if i == 0:
requests_idx_mapping = batch.requests_idx_mapping requests_idx_mapping = batch.requests_idx_mapping
@ -384,6 +402,12 @@ class Seq2SeqLMBatch(Batch):
), ),
) )
if top_n_tokens_tensor is None:
top_n_tokens_tensor = batches[0].top_n_tokens_tensor.new_zeros(
total_batch_size,
)
top_n_tokens_tensor[start_index:end_index] = batch.top_n_tokens_tensor
# Copy to correct indices # Copy to correct indices
encoder_last_hidden_state[ encoder_last_hidden_state[
start_index:end_index, -batch.max_input_length :, : start_index:end_index, -batch.max_input_length :, :
@ -488,6 +512,8 @@ class Seq2SeqLMBatch(Batch):
read_offsets=read_offsets, read_offsets=read_offsets,
next_token_choosers=next_token_choosers, next_token_choosers=next_token_choosers,
stopping_criterias=stopping_criterias, stopping_criterias=stopping_criterias,
top_n_tokens=top_n_tokens,
top_n_tokens_tensor=top_n_tokens_tensor,
max_input_length=max_input_length, max_input_length=max_input_length,
max_decoder_input_length=max_decoder_input_length, max_decoder_input_length=max_decoder_input_length,
padding_right_offset=padding_right_offset, padding_right_offset=padding_right_offset,
@ -613,6 +639,12 @@ class Seq2SeqLM(Model):
batch.past_key_values, batch.past_key_values,
) )
batch_top_token_ids, batch_top_token_logprobs = batch_top_tokens(
batch.top_n_tokens,
batch.top_n_tokens_tensor,
torch.softmax(logits[:, -1], -1),
)
# Finished requests # Finished requests
generations: List[Generation] = [] generations: List[Generation] = []
stopped = True stopped = True
@ -628,6 +660,9 @@ class Seq2SeqLM(Model):
batch.next_token_choosers, batch.next_token_choosers,
batch.stopping_criterias, batch.stopping_criterias,
batch.all_decoder_input_ids, batch.all_decoder_input_ids,
batch.top_n_tokens,
batch_top_token_ids,
batch_top_token_logprobs,
) )
# For each member of the batch # For each member of the batch
@ -641,6 +676,9 @@ class Seq2SeqLM(Model):
next_token_chooser, next_token_chooser,
stopping_criteria, stopping_criteria,
all_decoder_input_ids, all_decoder_input_ids,
top_n_tokens,
top_token_ids,
top_token_logprobs,
) in enumerate(iterator): ) in enumerate(iterator):
# Select next token # Select next token
next_token_id, logprobs = next_token_chooser( next_token_id, logprobs = next_token_chooser(
@ -698,6 +736,24 @@ class Seq2SeqLM(Model):
else: else:
prefill_tokens = None prefill_tokens = None
if top_n_tokens > 0:
toptoken_texts = self.tokenizer.batch_decode(
top_token_ids,
clean_up_tokenization_spaces=False,
skip_special_tokens=False,
)
special_toptokens = [
token_id in self.all_special_ids for token_id in top_token_ids
]
top_tokens = TopTokens(
top_token_ids,
top_token_logprobs,
toptoken_texts,
special_toptokens,
)
else:
top_tokens = None
generation = Generation( generation = Generation(
request.id, request.id,
prefill_tokens, prefill_tokens,
@ -706,6 +762,7 @@ class Seq2SeqLM(Model):
next_token_text, next_token_text,
next_token_id_squeezed.item() in self.all_special_ids, next_token_id_squeezed.item() in self.all_special_ids,
generated_text, generated_text,
top_tokens,
) )
generations.append(generation) generations.append(generation)

23
server/text_generation_server/models/types.py
View File

@ -1,3 +1,4 @@
from functools import total_ordering
import torch import torch
from abc import ABC, abstractmethod from abc import ABC, abstractmethod
@ -71,6 +72,25 @@ class PrefillTokens:
return len(self.token_ids) return len(self.token_ids)
@dataclass
class TopTokens:
token_ids: List[int]
logprobs: List[float]
texts: List[str]
is_special: List[bool]
def to_pb(self) -> generate_pb2.TopTokens:
return generate_pb2.TopTokens(
ids=self.token_ids,
logprobs=self.logprobs,
texts=self.texts,
is_special=self.is_special,
)
def __len__(self):
return len(self.token_ids)
@dataclass @dataclass
class Generation: class Generation:
request_id: int request_id: int
@ -80,6 +100,8 @@ class Generation:
token_text: str token_text: str
token_is_special: bool token_is_special: bool
generated_text: Optional[GeneratedText] generated_text: Optional[GeneratedText]
# Optional for now, since it's not yet supported for every model.
top_tokens: Optional[TopTokens]
def to_pb(self) -> generate_pb2.Generation: def to_pb(self) -> generate_pb2.Generation:
return generate_pb2.Generation( return generate_pb2.Generation(
@ -94,4 +116,5 @@ class Generation:
generated_text=self.generated_text.to_pb() generated_text=self.generated_text.to_pb()
if self.generated_text is not None if self.generated_text is not None
else None, else None,
top_tokens=self.top_tokens.to_pb() if self.top_tokens is not None else None,
) )

11
server/text_generation_server/utils/layers.py
View File

@ -18,13 +18,20 @@ from accelerate import init_empty_weights
from text_generation_server.utils.gptq.quant_linear import QuantLinear from text_generation_server.utils.gptq.quant_linear import QuantLinear
HAS_EXLLAMA = True try:
major, _minor = torch.cuda.get_device_capability()
except Exception:
major = 1
HAS_EXLLAMA = False
CAN_EXLLAMA = major >= 8
if os.getenv("DISABLE_EXLLAMA") == "True": if os.getenv("DISABLE_EXLLAMA") == "True":
HAS_EXLLAMA = False HAS_EXLLAMA = False
elif CAN_EXLLAMA:
try: try:
from text_generation_server.utils.gptq.exllama import Ex4bitLinear from text_generation_server.utils.gptq.exllama import Ex4bitLinear
HAS_EXLLAMA = True
except ImportError: except ImportError:
HAS_EXLLAMA = False pass
from typing import Optional from typing import Optional

71
server/text_generation_server/utils/tokens.py
View File

@ -1,24 +1,20 @@
import re import re
from typing import Callable, List, Optional, Tuple
import torch import torch
from transformers import (
RepetitionPenaltyLogitsProcessor,
PreTrainedTokenizerBase,
)
from typing import List, Tuple, Optional
from text_generation_server.pb import generate_pb2 from text_generation_server.pb import generate_pb2
from text_generation_server.pb.generate_pb2 import FinishReason from text_generation_server.pb.generate_pb2 import FinishReason
from text_generation_server.utils.watermark import WatermarkLogitsProcessor
from text_generation_server.utils.logits_process import ( from text_generation_server.utils.logits_process import (
static_warper, HeterogeneousProcessorWrapper,
HeterogeneousRepetitionPenaltyLogitsProcessor, HeterogeneousRepetitionPenaltyLogitsProcessor,
HeterogeneousTemperatureLogitsWarper, HeterogeneousTemperatureLogitsWarper,
HeterogeneousTopKLogitsWarper, HeterogeneousTopKLogitsWarper,
HeterogeneousTopPLogitsWarper, HeterogeneousTopPLogitsWarper,
HeterogeneousTypicalLogitsWarper, HeterogeneousTypicalLogitsWarper,
HeterogeneousProcessorWrapper, static_warper,
) )
from text_generation_server.utils.watermark import WatermarkLogitsProcessor
from transformers import PreTrainedTokenizerBase, RepetitionPenaltyLogitsProcessor
class NextTokenChooser: class NextTokenChooser:
@ -229,11 +225,10 @@ class HeterogeneousNextTokenChooser:
scores = warper(input_ids, scores) scores = warper(input_ids, scores)
next_ids = self.choice(scores) next_ids = self.choice(scores)
next_logprobs = torch.gather( logprobs = torch.log_softmax(scores, -1)
torch.log_softmax(scores, -1), 1, next_ids.view(-1, 1) next_logprobs = torch.gather(logprobs, 1, next_ids.view(-1, 1)).view(-1)
).view(-1)
return next_ids, next_logprobs return next_ids, next_logprobs, logprobs
def filter(self, indices): def filter(self, indices):
if self.watermark_processor is not None: if self.watermark_processor is not None:
@ -339,3 +334,51 @@ class HeterogeneousSampling:
self.greedy_indices = new_greedy_indices self.greedy_indices = new_greedy_indices
self.sampling_mapping = new_sampling_mapping self.sampling_mapping = new_sampling_mapping
return self return self
def batch_top_tokens(
top_n_tokens: list[int], top_n_tokens_tensor: torch.Tensor, logprobs: torch.Tensor
) -> Tuple[List[List[int]], List[List[float]]]:
"""Find the top n most likely tokens for a batch of generations.
When multiple tokens have equal probabilities and they don't all fit, the
remaining tokens are also returned.
"""
max_top_n = max(top_n_tokens)
# Early exit when top_n_tokens is not used
if max_top_n == 0:
return [[]] * len(top_n_tokens), [[]] * len(top_n_tokens)
# Ensure top_n doesn't exceed vocab size
top_n_tokens = [min(tok, logprobs.size(-1)) for tok in top_n_tokens]
# Parallel kthvalue adapted from https://discuss.pytorch.org/t/how-to-efficiently-get-the-k-th-largest-values-in-parallel/160529/2
# Sorted topk is faster than torch.sort() since we only need a small subset
sorted_top_k = torch.topk(logprobs, k=max_top_n, dim=1, sorted=True).values
nth_highest = torch.gather(
sorted_top_k, 1, (top_n_tokens_tensor - 1).clip(min=0).unsqueeze(1)
)
nth_highest[nth_highest == -float("inf")] = torch.finfo(logprobs.dtype).min
# Find the new "fuzzy" top n values
top_n_indices = (logprobs >= nth_highest).nonzero()
_, top_n_ishes = torch.unique_consecutive(top_n_indices[:, 0], return_counts=True)
k = 1 if top_n_ishes.numel() == 0 else top_n_ishes.max()
# Take a new topk for these new max n values
top_k = torch.topk(logprobs, k=k, dim=1, sorted=True)
top_n_ishes = top_n_ishes.tolist()
top_indices = top_k.indices.tolist()
top_values = top_k.values.tolist()
return (
[
idxs[:n] if req_n > 0 else []
for idxs, n, req_n in zip(top_indices, top_n_ishes, top_n_tokens)
],
[
vals[:n] if req_n > 0 else []
for vals, n, req_n in zip(top_values, top_n_ishes, top_n_tokens)
],
)

14
server/text_generation_server/utils/weights.py
View File

@ -170,10 +170,11 @@ class Weights:
"Cannot load `gptq` weight, make sure the model is already quantized, or quantize it with `text-generation-server quantize ORIGINAL_MODEL_ID NEW_MODEL_ID`" "Cannot load `gptq` weight, make sure the model is already quantized, or quantize it with `text-generation-server quantize ORIGINAL_MODEL_ID NEW_MODEL_ID`"
) )
from text_generation_server.utils.layers import HAS_EXLLAMA from text_generation_server.utils.layers import HAS_EXLLAMA, CAN_EXLLAMA
if use_exllama: if use_exllama:
if not HAS_EXLLAMA: if not HAS_EXLLAMA:
if CAN_EXLLAMA:
logger.warning( logger.warning(
"Exllama GPTQ cuda kernels (which are faster) could have been used, but are not currently installed, try using BUILD_EXTENSIONS=True" "Exllama GPTQ cuda kernels (which are faster) could have been used, but are not currently installed, try using BUILD_EXTENSIONS=True"
) )
@ -222,6 +223,17 @@ class Weights:
return bits, groupsize return bits, groupsize
def _set_gptq_params(self, model_id): def _set_gptq_params(self, model_id):
filename = "config.json"
try:
if os.path.exists(os.path.join(model_id, filename)):
filename = os.path.join(model_id, filename)
else:
filename = hf_hub_download(model_id, filename=filename)
with open(filename, "r") as f:
data = json.load(f)
self.gptq_bits = data["quantization_config"]["bits"]
self.gptq_groupsize = data["quantization_config"]["group_size"]
except Exception:
filename = "quantize_config.json" filename = "quantize_config.json"
try: try:
if os.path.exists(os.path.join(model_id, filename)): if os.path.exists(os.path.join(model_id, filename)):