Lightning-AI / Lightning-AI/litgpt

Feature: Support for Multimodality

Open
#2,173 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

As my understanding (Please correct me if I'm wrong), currently LitGPT is not supporting Multimodality as the Pretrain, Finetune, Chat and Evals is not accepting any other modality inputs. I would like to help to support this if it's on the plan of improvements for LitGPT.

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

Review the existing pretrain, finetune, chat, and eval workflows to determine how they currently accept inputs. Define which modalities and model paths are in scope, then document completion criteria for multimodal support across those workflows.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, 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.