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

Support Pydantic 2

Browse Source 
This should allow users to use either Pydantic 2 or Pydantic 1.
This commit is contained in:
Jelle Zijlstra 2023-08-22 04:35:36 -07:00
parent c4422e5678
commit 856af1c03a
2 changed files with 16 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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"
aiohttp = "^3.8" aiohttp = "^3.8"
huggingface-hub = ">= 0.12, < 1.0" huggingface-hub = ">= 0.12, < 1.0"

30
clients/python/text_generation/types.py
View File

@ -18,21 +18,21 @@ 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
@ -106,7 +106,7 @@ 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
@ -139,7 +139,7 @@ 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
@ -174,7 +174,7 @@ 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
@ -188,13 +188,13 @@ 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]
# 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
@ -212,7 +212,7 @@ 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
@ -221,10 +221,10 @@ class StreamResponse(BaseModel):
token: Token token: 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