enacimie/madlad400-7b-mt-Q4_K_M-GGUF
Quantization vs google/madlad400-7b-mt. enacimie/madlad400-7b-mt-Q4_K_M-GGUF is a GGUF quantization (Q4_K_M) of the same weights: 244 tensors match exactly and 866 within quantization error.
Tensors changed: Attention 0/578, Norms 0/242, other 0/289, lm_head 0/1