mradermacher/pythia-70m-deduped-v0-i1-GGUF
Quantization vs EleutherAI/pythia-70m-deduped-v0. mradermacher/pythia-70m-deduped-v0-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 44 tensors match exactly and 20 within quantization error.
Tensors changed: Embeddings 0/2, Norms 0/26, Attention 0/12, MLP 0/24