mradermacher/statichh-pythia-1.4b-sft-GGUF
Same weights, converted vs ncgc/statichh-pythia-1.4b-sft. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/2, Attention 0/48, Norms 0/98, MLP 0/96
Same weights, converted vs ncgc/statichh-pythia-1.4b-sft. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/2, Attention 0/48, Norms 0/98, MLP 0/96