how to finetune llama-30b with fastchat？
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 39.5k
- Forks
- 4.8k
- PR merge metrics
- No merged PRs in 30d
Description
I want finetune llama 33b, it can not be finetune on 8 A100 GPU, It may need to use nnodes? Could you please provide a training script for llama 33b?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue mentions fine-tuning Llama 33B on 8 A100 GPUs and asks whether multiple nodes are needed, but names no files or tests. Start by locating FastChat's training entry points and existing fine-tuning documentation, then determine what a multi-node training script would need. Done means providing a working script or clear documented procedure for this setup.
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