Lightning-AI / Lightning-AI/lit-llama

Sequence classification with Lit-LLaMA

Open
#331 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
6.1k
Forks
517
PR merge metrics
No merged PRs in 30d

Description

I'm trying to use Lit-LLaMA with LoRA for a sequence classification problem involving a dataset of tweets, similar to `ought/raft`. A straightforward approach would be to follow the idea described in the T5 paper, which treats the problem as a text generation task and utilizes the logits/probabilities of the class label tokens. My question is whether this approach is suitable for (Lit-)LLaMA as well, or if there is a better alternative for tackling this problem.

Contributor guide

No contributing guide indexed for this repository

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 file, test, or entry point is named. Start by locating the Lit-LLaMA LoRA fine-tuning and sequence-task entry points, then determine whether the T5-style class-label approach is supported or whether a separate classification design is needed; done requires a decided approach and corresponding implementation.

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.