Configurable EOS Token Support #20
Merged
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Outdated suggestions cannot be applied.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.
Description
This pull request introduces the integration of models with different EOS tokens than those used by the default ExllamaV2 tokenizer. This change addresses the need for flexibility in model configurations without the necessity of hardcoding EOS tokens directly into the codebase.
Key Changes
Dynamic EOS Token Configuration: A new optional configuration parameter, eos_token, has been added to the config.ini file. This parameter allows different models to specify their own EOS tokens directly via the configuration file, thus enabling seamless integration of models with unique tokenization requirements.
Default Behavior: If the eos_token key is not present in config.ini, the system will default to using tokenizer.eos_token_id. This ensures backward compatibility and default behavior that aligns with the ExllamaV2 tokenizer's specifications.
Custom EOS Token Support: For models requiring a distinct EOS token, such as Llama3, users can now specify this by adding eos_token = under the appropriate section in the config.ini file. This entry should be followed by the specific EOS token value as needed.
Usage
Users who need to configure a custom EOS token for a model should add or update the eos_token entry in the config.ini file under the relevant model section. For example:
p.s. This should also cover PR #17 , as it was worked from the branch pushed yesterday.