mlx-community/Soprano-1.1-80M-bf16

Same weights, repacked vs ekwek/Soprano-1.1-80M. Same weights in different files (re-saved, re-sharded or new metadata), plus 80 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/69, MLP 0/51, Attention 0/68

On the Hub · Downloads on Model Pulse