NVIDIA-NeMo / NVIDIA-NeMo/RL

Qwen3.8 27B RL validation and recipe

Open
#3,675 0 comments 0 reactions 1 assignee Assigned to @terrykong View on GitHub
Documentation enhancement Feature
Dominant language
Python
Stars
2k
Forks
561
Avg merge
4d 5h
Merged PRs (30d)
145

Description

Verify RL training for Qwen3.8 27B, AutoModel and Mcore backend, provide the sample recipes and docs.

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.