mradermacher/CodeShell-7B-i1-GGUF
Quantization vs WisdomShell/CodeShell-7B. mradermacher/CodeShell-7B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 338 tensors match exactly and 169 within quantization error.
Tensors changed: Attention 0/168, Norms 0/170, MLP 0/168, Embeddings 0/1