tamewild/PCSS-Qwen3.5-9B

Partial fine-tune vs Qwen/Qwen3.5-9B-Base. Partial change: 74% of the weights changed (attention, mlp, other), in 32 of 32 layers.

Tensors changed: lm_head 0/1, Embeddings 0/5, MLP 99/211, Attention 156/336, other 1/1, Norms 0/221

On the Hub · Downloads on Model Pulse