ml-explore / ml-explore/mlx-examples

ChatML / convert models with added/special tokens?

Open
#119 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
9k
Forks
1.2k
PR merge metrics
No merged PRs in 30d

Description

looks like the params.json argument that's expected in the lora example doesn't support added/special tokens for the conversion script.

looking to convert nous models and would love help/advice on accommodating chatML format tokens into mlx conversion.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the lora example's params.json argument and the conversion script, focusing on how added or special tokens are represented. Determine the required handling for ChatML tokens when converting Nous models; done means the conversion supports those tokens without losing their intended behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.