THUDM / THUDM/slime

[Question] Do we support the SAO method used in the training of GLM-5.2

Open
#2,212 0 comments 5 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Your Question

Do we have plan open source of the SAO and CompactionRL methods used in the training of GLM-5.2

What I've Tried

nothing

Environment (if relevant)
  • slime version:
  • Python version:
  • PyTorch version:
  • CUDA/ROCm version:
  • GPU type and count:
  • OS:
Additional Context

No response

Pre-submission Checklist

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

No source file, test, or implementation entry point is identified. Start with the linked documentation and FAQ, then review the project scope around RL post-training to determine whether SAO or CompactionRL support is planned. Done means documenting a clear maintainer answer about support or open-sourcing plans.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.