Fixing qwen2. (#1818)

# 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

 -->
This commit is contained in:
Nicolas Patry 2024-04-26 19:19:08 +02:00 committed by GitHub
parent a8fd4236eb
commit 8b8e8f6632
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 4 deletions

View File

@ -4,7 +4,7 @@ import torch
import torch.distributed import torch.distributed
from opentelemetry import trace from opentelemetry import trace
from transformers.models.qwen2 import Qwen2Tokenizer from transformers import AutoTokenizer, AutoConfig
from typing import Optional from typing import Optional
from text_generation_server.models.cache_manager import BLOCK_SIZE from text_generation_server.models.cache_manager import BLOCK_SIZE
@ -15,7 +15,6 @@ from text_generation_server.models.flash_mistral import (
from text_generation_server.models.custom_modeling.flash_qwen2_modeling import ( from text_generation_server.models.custom_modeling.flash_qwen2_modeling import (
Qwen2ForCausalLM, Qwen2ForCausalLM,
) )
from transformers.models.qwen2 import Qwen2Config
from text_generation_server.utils import ( from text_generation_server.utils import (
initialize_torch_distributed, initialize_torch_distributed,
weight_files, weight_files,
@ -42,7 +41,7 @@ class FlashQwen2(BaseFlashMistral):
else: else:
raise NotImplementedError("FlashQwen2 is only available on GPU") raise NotImplementedError("FlashQwen2 is only available on GPU")
tokenizer = Qwen2Tokenizer.from_pretrained( tokenizer = AutoTokenizer.from_pretrained(
model_id, model_id,
revision=revision, revision=revision,
padding_side="left", padding_side="left",
@ -50,7 +49,7 @@ class FlashQwen2(BaseFlashMistral):
trust_remote_code=trust_remote_code, trust_remote_code=trust_remote_code,
) )
config = Qwen2Config.from_pretrained( config = AutoConfig.from_pretrained(
model_id, revision=revision, trust_remote_code=trust_remote_code model_id, revision=revision, trust_remote_code=trust_remote_code
) )
config.quantize = quantize config.quantize = quantize