lm-sys / lm-sys/FastChat

Fine-tuning Falcon

Open
#1,588 4 comments 6 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

When I try to train Vicuna against Falcon it fails,

The big thing is the padding, since Falcon has no padding. (that is the part I can't figure out myself)

Also Falcon doesn't have flash attention, so there needs to be a new monkey script to swap flash attention for Falcon. (I could probably figure this part out, if the padding part was working)

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 reproducing the reported Vicuna-against-Falcon training failure and tracing how padding is handled for Falcon. Then inspect the existing flash-attention monkey scripts and define the fallback behavior; done means Falcon fine-tuning runs successfully with padding and without flash attention.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
28/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.