Kewk/Heretical-Qwen3.5-9B
Full fine-tune vs Qwen/Qwen3.5-9B-Base. Fine-tune: 96% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 2/4, MLP 100/208, Attention 197/332, Norms 107/215
3 derivatives checked
- mradermacher/Heretical-Qwen3.5-9B-i1-GGUF: Quantization
- mradermacher/Heretical-Qwen3.5-9B-GGUF: Same weights, converted
- Lordmo/Heretical-Qwen3.5-9B-i1-GGUF: Quantization