Add DeepSeek v4 tool parser#22
Open
spicyneuron wants to merge 2 commits into
Open
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds preliminary tool parsing support.
I copied the hidden but presumably official chat template into one of your quants, and ran against the official encoding tests to validate.
Tool calls seem to work as expected via mlx-lm server + Anthropic proxy + Claude Code.
Worth noting,
mlx-lmmatches tool calls at the token-level, which is different than the official repo's\n\n<｜DSML｜tool_callsstring. The newlines aren't reliable matched because white space can get tokenized with punctuation (ex:.\n\n). So I opted to match on<｜DSML｜tool_callsinstead.That works reliably but means newlines slip into message content. The fix would need to touch
server.py, so I left it out for now. Open to other suggestions.