HF tokenizer_call_args #793
Open
+13
−1
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
| @@ -71,6 +71,9 @@ def collect_model_arg(name: str) -> Any | None: | |||
| tokenizer_path = collect_model_arg("tokenizer_path") | |||
| self.batch_size = collect_model_arg("batch_size") | |||
| self.chat_template = collect_model_arg("chat_template") | |||
| self.tokenizer_call_args = collect_model_arg("tokenizer_call_args") | |||
There was a problem hiding this comment.
How about just tokenizer_args?
There was a problem hiding this comment.
@alexandrasouly-aisi Are you okay w/ the change to tokenizer_args?
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Outdated suggestions cannot be applied.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.
This PR contains:
I am trying to add strongreject to inspect evals, and some parts use a HF model with a small context length, so they use the tokeniser to truncate the input. I would like the tokenizer call to be more flexible take custom arguments.
What is the current behavior? (You can also link to an open issue here)
HF tokenizer is called with default parameters
tokenizer(response, max_length=max_response_length, truncation=True)What is the new behavior?
The API would take a
tokenizer_call_argsdict to be passed onto the tokenizer call.Does this PR introduce a breaking change? (What changes might users need to make in their application due to this PR?)
No
Other information: