DarkKitsune/Qwen3.5-9B-Qworus-V2

Full fine-tune vs empero-ai/Qwen3.8-9B-Distill. Fine-tune: 95% of the weights changed, across 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 1/4, Norms 87/215, Attention 203/332, MLP 96/208

1 derivatives checked

• charlieduzstuf/Qwable-Ex: Full fine-tune

On the Hub · Downloads on Model Pulse