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Outdated suggestions cannot be applied.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.
Add eos_token_id from the generation config file so that Llama3 can perform inference correctly.
Why are these changes needed?
The addition of eos_token_id from the generation config file to the stop_token_ids is crucial for ensuring correct inference termination in frameworks like Llama3. Typically, the eos_token_id used for model inference can be sourced from the tokenizer's config file and is usually identical to the one in the model's generation config. However, for certain models like Llama3, discrepancies between these two can prevent inference from stopping correctly. By explicitly specifying the eos_token_id from the generation config, our framework can handle inference more accurately and support a wider range of models.
Related issue number (if applicable)
N/A
Checks
format.sh
to lint the changes in this PR.