WingNews GitHub [2]

stefanwebb's submissions

Open source x 3: GRPO training with OpenEnv, vLLM, and Oumi (github.com)

3 pts| 4 months ago | discuss

Is more training data always better? (blog.oumi.ai)

3 pts| 5 months ago | 2 comments

Small Fine-Tuned Models Are All You Need (blog.oumi.ai)

6 pts| 5 months ago | 2 comments

Custom AI models in hours not months with auto Data Synth and LLM-as-a-Judge (blog.oumi.ai)

3 pts| 5 months ago | 1 comment

page 1