Lightning-AI / Lightning-AI/litgpt

Fine-Tuning Chat Model with Domain-Specific Data for custom dataset

Open
#1,877 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

help wanted question
Dominant language
Python
Stars
13.7k
Forks
1.5k
Avg merge
15h 37m
Merged PRs (30d)
1

Description

I have domain-specific data that I've preprocessed from PDFs into a c4_demo.json format, where each entry looks like [{"text": "<data from file1.pdf"}]. Now, I want to fine-tune my model for chat-based interactions to generate structured chat outputs. My dataset is currently in the following format: [{"role": "system", "content": ""}, {"role": "user", "content": ""}, {"role": "assistant", "content": ""}, ...]. Which fine-tuning method should I use for this?

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 mentions c4_demo.json and a role/content dataset, but no source file, test, or entry point. Start by reviewing LitGPT’s existing fine-tuning recipes for custom datasets and comparing the two formats shown; done means identifying a supported path for structured chat outputs.

Written by the indexing model from the issue text.

Assessment

Tech stack
machine-learning, python
Domain
ai, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.