stefanwebb

Recent Submissions

1. 1. ▲ Open source x 3: GRPO training with OpenEnv, vLLM, and Oumi (github.com) 3 points · 3 months ago · 0 comments
2. 2. ▲ Is more training data always better? (blog.oumi.ai) 3 points · 3 months ago · 2 comments
3. 3. ▲ Small Fine-Tuned Models Are All You Need (blog.oumi.ai) 6 points · 4 months ago · 2 comments
4. 4. ▲ Custom AI models in hours not months with auto Data Synth and LLM-as-a-Judge (blog.oumi.ai) 3 points · 4 months ago · 1 comment