Add Gemma-4 float16 UNSLOTH_FORCE_FLOAT32 patches for GRPO stability#1
Closed
danielhanchen wants to merge 7 commits into
Closed
Add Gemma-4 float16 UNSLOTH_FORCE_FLOAT32 patches for GRPO stability#1danielhanchen wants to merge 7 commits into
danielhanchen wants to merge 7 commits into
Enhance your code review process with GitHub Actions
GitHub Actions make it easy to automate all your software workflows, now with world-class CI/CD.
Build, test, and deploy your code right from GitHub. Learn more about GitHub Actions.
Linux, macOS, Windows, and containers
Matrix builds
Any language
Live logs
Built-in secret store
