chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2-MLX-bf16

Partial fine-tune vs chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-v2. Partial change: 0% of the weights changed (norms), in 24 of 24 layers.

Tensors changed: Embeddings 0/1, Norms 61/79, Attention 0/150, MLP 0/72

On the Hub · Downloads on Model Pulse