THUDM / THUDM/slime

More details about the examples of on-policy distillation

Open
#1,493 4 comments 1 reaction 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

Thanks your fantastic job!

Could you provide more details about the examples of on-policy distillation? It is mentioned in examples/on_policy_distillation/Readme.md that the Qwen3-8B-Base model fine-tuned with supervised fine-tuning (SFT) on part of the [OpenThoughts3-1.2M] dataset is used. Would it be possible to make this SFT model publicly available, or inform us of the SFT details such as the number of epochs and the learning rate?

@ahxt

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

Review examples/on_policy_distillation/Readme.md and the referenced Qwen3-8B-Base SFT description. Confirm the SFT model's availability and the training details requested, then update the example documentation with information supplied by the maintainers. Done means the README clearly documents those details or explains that the model or details cannot be shared.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.