Add Gemma-4 float16 UNSLOTH_FORCE_FLOAT32 patches for GRPO stability#3
Open
danielhanchen wants to merge 11 commits into
Open
Add Gemma-4 float16 UNSLOTH_FORCE_FLOAT32 patches for GRPO stability#3danielhanchen wants to merge 11 commits into
danielhanchen wants to merge 11 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
