squ11z1/Hypnos-Q1

Full fine-tune vs Qwen/Qwen3.5-4B. Fine-tune: 91% of the weights changed, across 32 of 32 layers.

Tensors changed: MLP 96/196, Attention 177/320, Norms 49/203, Embeddings 0/3

1 derivatives checked

• squ11z1/Hypnos-Q1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse