mradermacher/pythia-70m-deduped-v0-GGUF
Same weights, converted vs EleutherAI/pythia-70m-deduped-v0. Same weights stored in another dtype (F16/U8 → F16/F32).
Tensors changed: Embeddings 0/2, Norms 0/26, Attention 0/12, MLP 0/24
Same weights, converted vs EleutherAI/pythia-70m-deduped-v0. Same weights stored in another dtype (F16/U8 → F16/F32).
Tensors changed: Embeddings 0/2, Norms 0/26, Attention 0/12, MLP 0/24