p-e-w/Qwen3.5-4B-heretic

Full fine-tune vs Qwen/Qwen3.5-4B-Base. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 2/4, MLP 100/196, Attention 201/320, Norms 107/203

1 derivatives checked

• Biomanticus/Qwen3.5-4B-heretic-gguf: Same weights, converted

On the Hub · Downloads on Model Pulse