ml-explore / ml-explore/mlx-examples

What's a good data format for lora fine-tuning?

Open
#258 4 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

I know the recommended format is this:
{"text": "Q:What is the capital of France?\nA:The capital of France is Paris."}

But some base model like Solar 10.4B recommends:
.### User:
What's the meaning of the word 'duck' in the following context?

.### Context:
The anthology of classic games is replete with instances where a skillful duck altered the trajectory of bridge history.

.### Assistant:
A skill in the game of bridge.

How should I adapt the format? Thanks!

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

The issue names no target file, test, or entry point. Start by comparing the recommended JSON example with Solar 10.4B's prompt template; done means documenting an agreed training-data format and any required adaptation.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.