mlx-community/Qwopus3.8-27B-Flash-V2-bf16
Partial fine-tune vs Jackrong/Qwopus3.8-27B-Flash-V2. Partial change: 0% of the weights changed (norms), in 64 of 64 layers.
Tensors changed: Norms 161/209, Attention 0/400, MLP 0/192, Embeddings 0/1
Partial fine-tune vs Jackrong/Qwopus3.8-27B-Flash-V2. Partial change: 0% of the weights changed (norms), in 64 of 64 layers.
Tensors changed: Norms 161/209, Attention 0/400, MLP 0/192, Embeddings 0/1