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