mradermacher/pythia-2.8b-sft-GGUF
Same weights, converted vs ncgc/pythia-2.8b-sft. 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 ncgc/pythia-2.8b-sft. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/2, Attention 0/64, Norms 0/130, MLP 0/128