hs-hf/madlad400-3b-mt-gguf
Same weights, converted vs google/madlad400-3b-mt. Same weights stored in another dtype (F32 → F16/F32), plus 1 new tensors.
Tensors changed: Attention 0/386, Norms 0/162, other 0/192, lm_head 0/1
Same weights, converted vs google/madlad400-3b-mt. Same weights stored in another dtype (F32 → F16/F32), plus 1 new tensors.
Tensors changed: Attention 0/386, Norms 0/162, other 0/192, lm_head 0/1