debug: correct token order #5
Merged
+20
−3
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
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Outdated suggestions cannot be applied.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.
Make sure to read the contributing guidelines before submitting a PR
@sfallah
llama-mtmd-cli applies a chat template to input texts/images and appends image tokens after text tokens by default. However, it looks like DeepSeek-OCR doesn't work if images follow texts. By swapping the order of <image> and the text, the model outputs only two tokens ("}" and EOS). This doesn't look like a bug in the original model, but I don't know if this is intentional or not.
Therefore, I changed a bit of how llama-mtmd-cli tokenizes the input. There could be a better way to do this though.
In correct order:
In reverse order: