mradermacher/Pythia-2.8B-HH-RLHF-Iterative-SamPO-GGUF

Same weights, converted vs jiazhengli/Pythia-2.8B-HH-RLHF-Iterative-SamPO. Same weights stored in another dtype (F16 → F16/F32).

Tensors changed: Embeddings 0/2, Attention 0/64, Norms 0/130, MLP 0/128

On the Hub · Downloads on Model Pulse