mradermacher/orpo_pythia2_hh_helpful-GGUF
Same weights, converted vs sert121/orpo_pythia2_hh_helpful. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/2, Attention 0/64, Norms 0/130, MLP 0/128
Same weights, converted vs sert121/orpo_pythia2_hh_helpful. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/2, Attention 0/64, Norms 0/130, MLP 0/128