fix custom vllm eval args #2325
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
vllm_utils.py可以还原一下不, 怎么改了这么多哇 |
swift/llm/utils/vllm_utils.py
Outdated
| @@ -260,12 +270,24 @@ def __post_init__(self): | |||
| self.top_k = -1 | |||
| if self.stop is None: | |||
| self.stop = [] | |||
| if self.repetition_penalty is None: | |||
There was a problem hiding this comment.
可以在eval.py中对None进行过滤不
自动lint工具修改的，改了一些格式，vllm_utils.py还原了 |
swift/llm/utils/vllm_utils.py
Outdated
| @@ -620,5 +620,6 @@ def prepare_vllm_engine_template(args: InferArguments, use_async: bool = False) | |||
| args.truncation_strategy, | |||
| model=llm_engine, | |||
| tools_prompt=args.tools_prompt) | |||
| logger.info(f'system: {template.default_system}') | |||
| args.system = template.default_system | |||
There was a problem hiding this comment.
It was likely modified by mistake and has been restored.
swift/llm/eval.py
Outdated
| if max_new_tokens is not None: | ||
| infer_cfg['max_tokens'] = max_new_tokens | ||
| defaults = {'repetition_penalty': 1.0, 'top_p': 1.0, 'top_k': -1} | ||
| # 使用默认值覆盖 None 值 |
Jintao-Huang
approved these changes
Oct 23, 2024
|
thank you for your PR! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR type
PR information
Fix eval dataset with vllm inference backend args.
Add following in
ms-swift/swift/llm/utils/vllm_utils.pyExperiment results
Paste your experiment result here(if needed).