Fix loading models which have their eos token disabled #7363
+5
−1
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
Some models, for instance IQuest-Coder-V1-40B-Instruct do not use an
eos token and disable it in the metadata:
32: BOOL | 1 | tokenizer.ggml.add_eos_token = False
We still try to access it, which leads to an error when attempting to
load the model. Handle it the same way as missing bos tokens, by setting
it to an empty string.
This fixes model loading, however the user must still manually specify
the proper stopping string in the parameters tab for such models to
work.
Owner
|
Thanks for the fix. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Some models, for instance IQuest-Coder-V1-40B-Instruct do not use an eos token and disable it in the metadata:
We still try to access it, which leads to an error when attempting to load the model. Handle it the same way as missing bos tokens, by setting it to an empty string.
This fixes model loading, however the user must still manually specify the proper stopping string in the parameters tab for such models to work.
Checklist: