lm-sys / lm-sys/FastChat

Clarification problem: Get confused for Fine-tuning Vicuna-7B with Local GPUs

Open
#1,514 0 comments 0 reactions 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

Hi Vicuna authors,

I noticed that in [fine-tuning vicuna demo code](https://github.com/lm-sys/FastChat/tree/51ed4fab89f61988e8395a3268595f1effb8528f#fine-tuning-vicuna-7b-with-local-gpus), the `--model_name_or_path` is set as `~/model_weights/llama-7b` instead of lacuna-7b.

Does it mean this script just provide a way how you train the vicuna from llama? Instead of further fine-tuning the vicuna from `--data_path playground/data/dummy.json`?

Can you clarify what's the real function for this script? 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

Read the linked fine-tuning Vicuna demo at the referenced commit, focusing on --model_name_or_path and --data_path playground/data/dummy.json. Confirm the script's intended training flow, then clarify its purpose and expected model path in the relevant documentation.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
documentation, machine-learning
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.