tensorblock/pythia-410m-deduped-GGUF
Quantization vs EleutherAI/pythia-410m-deduped. tensorblock/pythia-410m-deduped-GGUF is a GGUF quantization (Q2_K) of the same weights: 170 tensors match exactly and 74 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/98, Attention 0/48, MLP 0/96