tokimoa/apertus-v1.5-8b-mlx-bf16
Same weights, repacked vs swiss-ai/Apertus-v1.5-8B. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: MLP 0/128, Norms 0/129, Attention 0/128, lm_head 0/1
Same weights, repacked vs swiss-ai/Apertus-v1.5-8B. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: MLP 0/128, Norms 0/129, Attention 0/128, lm_head 0/1