Davd-b01/qwen3.8-flash-next-40b-prune-research

Partial fine-tune vs Qwen/Qwen3.8-Flash-Next. Partial change: 60% of the weights changed (attention, embeddings, mlp, other), in 48 of 48 layers.

Tensors changed: Norms 0/294, other 1/5, Attention 138/600, MLP 128/448, Embeddings 3/7, lm_head 0/1

On the Hub · Downloads on Model Pulse