ml-explore / ml-explore/mlx-examples
Jamba Model Conversion to MLX
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 9k
- Forks
- 1.2k
- PR merge metrics
- No merged PRs in 30d
Description
I've been trying to convert Jamba into MLX for more efficient training and usability but am having a difficult time. My specialty is in the training/datasets world and not the strongest in the core math behind the model architectures beyond the basic implementations.
Would somebody know of an easier way to get Jamba converted into MLX? I truly think Jamba has A LOT to offer and could do some awesome stuff in the MLX format and for local model training with Mac
I've provided the modeling script released by AI21 for quick reference. Is this feasible or just way too complicated at the moment?
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 attached modeling_jamba.txt to understand the AI21 Jamba architecture and conversion requirements. Then determine whether the requested MLX conversion is feasible within mlx-examples; done would mean a working Jamba conversion suitable for local Mac training, with the required behavior demonstrated.
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
- 25/100