lm-sys / lm-sys/FastChat

How to finetune mistral-7b with fastchat?

Open
#3,449 1 comment 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
39.5k
Forks
4.8k
PR merge metrics
No merged PRs in 30d

Description

When I use fastchat to finetune llama2, everything is ok. But when I want to finetune mistral, it shows that "transformer layer not found". I know the main reason is that the value of `--fsdp_transformer_layer_cls_to_wrap` should not be `LlamaDecoderLayer`. But what should it be set? Hope you can solve my problem. Many thanks!

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

Start with FastChat's fine-tuning entry points and the Mistral model configuration, focusing on the --fsdp_transformer_layer_cls_to_wrap option and the reported transformer-layer lookup error. Confirm the appropriate class setting for Mistral and document a working fine-tuning invocation and expected result.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.