Lightning-AI / Lightning-AI/litgpt

Finetune LLM model for Classification task

Open
#1,839 0 comments 2 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 am following your book content *Build a Large Language Model (From Scratch)*
Its really great if anybody want to get
https://www.amazon.com/Build-Large-Language-Model-Scratch/dp/1633437167

I did not find much resources / examples for classification fine tuning using litgpt let me know if you have made?

1) How to change final layer from vocab size to 2 for spam message spam classification
2) How to adjust code for data with Text and Labels instead of json type custom dataset for instruction
which files i need to modified to get results

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

No files, tests, or entry points are named in the issue. Begin by locating LitGPT's fine-tuning and custom-dataset entry points, then determine whether classification fine-tuning is documented or supported; done means a reproducible spam-classification example explains the two-class output and Text/Labels data path.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, machine-learning
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.