lm-sys / lm-sys/FastChat

Finetuning Llama3-8B fails due to lack of a PAD token in new tokenizer

Open
#3,266 13 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

I attempted a workaround, but the output from finetuning doesn't look quite right. Has anyone made a working fix for this issue?

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

The issue names no file, test, or entry point; begin by reproducing Finetuning Llama3-8B with the new tokenizer and tracing the PAD-token handling. Done means a documented fix that completes finetuning and produces correct-looking output, with validation against the reported failure.

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
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.