SpectralPO
/

s1K-7B-RSPO-neg

Model card Files Files and versions

Metrics Training metrics Community

README.md exists but content is empty.

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including SpectralPO/s1K-7B-RSPO-neg

Offline RL with Neg Samples

3 items • Updated Apr 27