Add add_bos_token for Llama3 evaluation
#2179
Merged
Conversation
This file contains hidden or 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
Signed-off-by: Kaihui-intel <[email protected]>
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR introduces a fix by adding an "--add_bos_token" argument to support proper evaluation when the model is fine-tuned with a beginning-of-sequence token.
- Added an argument for "add_bos_token" in the CLI parser
- Modified the function call to include the "add_bos_token" parameter for evaluation
...age-modeling/quantization/transformers/weight_only/text-generation/run_generation_cpu_woq.py
Outdated
Show resolved
Hide resolved
Co-authored-by: Copilot <[email protected]>
Contributor
|
|
XuehaoSun
approved these changes
Apr 23, 2025
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Outdated suggestions cannot be applied.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.
Type of Change
bug fix
Description
model: meta-llama/Llama-3.1-8B-Instruct
add_bos_tokendefault is False.If the model was trained or fine-tuned with a BOS token, this may lead to incorrect results.
Expected Behavior & Potential Risk
the expected behavior that triggered by this PR
How has this PR been tested?
how to reproduce the test (including hardware information)
Dependency Change?
any library dependency introduced or removed