lm-sys / lm-sys/FastChat

Question on the Security Improvements in Vicuna-7B-v1.5

Open
#3,002 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

Hello,

During my testing, I've noticed a significant improvement in security with Vicuna-7B-v1.5 compared to previous versions. I am curious to know the reason behind this enhancement. Is it because the model was trained on top of Llama-2-7B-Chat, or did you incorporate a larger set of safety data into the 125k dataset used for training this version?

Thank you for your time and effort.

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 by reviewing the Vicuna-7B-v1.5 training context and the 125k dataset mentioned in the issue. Done means providing a documented answer about whether the security improvement comes from Llama-2-7B-Chat, additional safety data, or both; no files or tests are identified.

Written by the indexing model from the issue text.

Assessment

Domain
ai, machine-learning
Issue type
Documentation
Difficulty
1/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.