mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-20 06:12:07 +00:00
e3d765645a
# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflects the extent of your awesome contribution. Then, please replace this with a description of the change and which issue is fixed (if applicable). Please also include relevant motivation and context. List any dependencies (if any) that are required for this change. Once you're done, someone will review your PR shortly (see the section "Who can review?" below to tag some potential reviewers). They may suggest changes to make the code even better. If no one reviewed your PR after a week has passed, don't hesitate to post a new comment @-mentioning the same persons---sometimes notifications get lost. --> <!-- Remove if not applicable --> Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. <!-- Your PR will be replied to more quickly if you can figure out the right person to tag with @ @OlivierDehaene OR @Narsil --> --------- Co-authored-by: Joshua Rosenkranz <joshua.rosenkranz@gmail.com>
82 lines
2.7 KiB
Python
82 lines
2.7 KiB
Python
import torch
|
|
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|
from typing import List, Optional, Tuple
|
|
|
|
from text_generation_server.models import CausalLM
|
|
|
|
|
|
class RW(CausalLM):
|
|
def __init__(
|
|
self,
|
|
model_id: str,
|
|
revision: Optional[str] = None,
|
|
quantize: Optional[str] = None,
|
|
speculator: Optional[str] = None,
|
|
dtype: Optional[torch.dtype] = None,
|
|
trust_remote_code: bool = False,
|
|
):
|
|
if speculator:
|
|
raise RuntimeError("Medusa decoding is not enabled for AutoModel")
|
|
|
|
if torch.cuda.is_available():
|
|
device = torch.device("cuda")
|
|
dtype = torch.float16 if dtype is None else dtype
|
|
else:
|
|
if quantize:
|
|
raise ValueError("quantization is not available on CPU")
|
|
|
|
device = torch.device("cpu")
|
|
dtype = torch.float32 if dtype is None else dtype
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(
|
|
model_id,
|
|
revision=revision,
|
|
padding_side="left",
|
|
truncation_side="left",
|
|
trust_remote_code=trust_remote_code,
|
|
)
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|
model_id,
|
|
revision=revision,
|
|
torch_dtype=dtype,
|
|
device_map=(
|
|
"auto"
|
|
if torch.cuda.is_available() and torch.cuda.device_count() > 1
|
|
else None
|
|
),
|
|
load_in_8bit=quantize == "bitsandbytes",
|
|
trust_remote_code=trust_remote_code,
|
|
)
|
|
if torch.cuda.is_available() and torch.cuda.device_count() == 1:
|
|
model = model.cuda()
|
|
|
|
if tokenizer.pad_token_id is None:
|
|
if model.config.pad_token_id is not None:
|
|
tokenizer.pad_token_id = model.config.pad_token_id
|
|
elif model.config.eos_token_id is not None:
|
|
tokenizer.pad_token_id = model.config.eos_token_id
|
|
elif tokenizer.eos_token_id is not None:
|
|
tokenizer.pad_token_id = tokenizer.eos_token_id
|
|
else:
|
|
tokenizer.add_special_tokens({"pad_token": "[PAD]"})
|
|
|
|
super(CausalLM, self).__init__(
|
|
model=model,
|
|
tokenizer=tokenizer,
|
|
requires_padding=True,
|
|
dtype=dtype,
|
|
device=device,
|
|
)
|
|
|
|
def forward(
|
|
self, input_ids, attention_mask, position_ids, past_key_values: Optional = None
|
|
) -> Tuple[torch.Tensor, List[Tuple[torch.Tensor, torch.Tensor]]]:
|
|
# Model Forward
|
|
outputs = self.model.forward(
|
|
input_ids=input_ids,
|
|
attention_mask=attention_mask,
|
|
past_key_values=past_key_values,
|
|
)
|
|
return outputs.logits, outputs.past_key_values
|