thirteenbit/madlad400-10b-mt-gguf
Quantization vs google/madlad400-10b-mt. thirteenbit/madlad400-10b-mt-gguf is a GGUF quantization (Q8_0) of the same weights: 164 tensors match exactly and 578 within quantization error.
Tensors changed: Attention 0/386, Norms 0/162, other 0/193, lm_head 0/1