Lightning-AI / Lightning-AI/lit-llama

Converting from lit-llama to HF checkpoint?

Open
#484 0 comments 2 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

Hello,
Thanks for the great work! I have a pre-trained Lit-Llama checkpoint that I'd like to convert to a format supported by HF, so that I could use it as an off-the-shelf model for other evaluation suites (e.g., lm-eval-harness). I'm wondering if this is currently possible? From snooping around, it looks like there's been some work in #150 but not sure what came of it. Thank you in advance!

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

Review the checkpoint-conversion work referenced in issue #150 and identify the existing Lit-Llama checkpoint entry points. Determine whether the result can be loaded as a Hugging Face checkpoint and used by lm-eval-harness; done means a documented, working conversion path.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python
Domain
machine-learning
Issue type
Feature
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.