jwest33/qwen3.5-9b-null-space-abliterated

Partial fine-tune vs Qwen/Qwen3.5-9B. Partial change: 84% of the weights changed (attention, lm_head, mlp), in 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 0/4, MLP 96/208, Attention 152/332, Norms 0/215

2 derivatives checked

• mradermacher/qwen3.5-9b-null-space-abliterated-i1-GGUF: Quantization
• mradermacher/qwen3.5-9b-null-space-abliterated-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse