mradermacher/orpo-phi2-GGUF

Same weights, converted vs Amu/orpo-phi2. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/66, MLP 0/128, Attention 0/256, lm_head 0/2

On the Hub · Downloads on Model Pulse