THUDM / THUDM/slime

Use LLM-based reward scores in custom-rm-path.

Open
#1,308 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
8.5k
Forks
1.3k
Avg merge
5h 36m
Merged PRs (30d)
22

Description

If I want to use an LLM to obtain a reward score for a response, how should I specify this in the custom-rm-path?

May I refer to the implementation of examples/on_policy_distillation? Is the LLM-based reward score used as a teacher model?

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 reading the custom-rm-path implementation and the examples/on_policy_distillation example. Trace how reward scores are configured and determine whether an LLM-based reward is supported and whether it serves as a teacher model; document the supported configuration and clarify the example's behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.