ml-explore / ml-explore/mlx-examples
[Feature Request] A better Finetune method
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 9k
- Forks
- 1.2k
- PR merge metrics
- No merged PRs in 30d
Description
Hi MLX team,
Just read about a new way to Finetune, seem promising:
https://twitter.com/Rui45898440/status/1772996453557997924
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the linked paper (2403.17919) and the referenced LMFlow repository to understand the proposed finetuning method. Then compare it with the repository's existing examples, which are not named in this issue. Done would require a defined integration scope, implementation location, and validation criteria.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100