LAION-AI / LAION-AI/Open-Assistant

Supervised Fine-tuning with Vicuna

Open
#3,645 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
37.4k
Forks
3.3k
PR merge metrics
No merged PRs in 30d

Description

Hi, I've seen vicuna model here. It seems like a pretty good model and supports lots of other languages (like Persian) other of the box. It speaks farsi but not that good.

I want to fine-tune it using supervised fine-tuning. How is it possible?

I've seen that you we can do an SFT here. But is there any tutorial?

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

Start by reviewing model/model_training/trainer_sft.py and the linked Vicuna and Open Assistant materials. Determine what supervised fine-tuning steps are currently documented and what a Vicuna tutorial would need to cover. Done means adding a clear tutorial or documented procedure for fine-tuning Vicuna with the existing project workflow.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
documentation, 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.