ansulev/Qwen3.5-9B-heretic-v2
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
2 derivatives checked
- mradermacher/Qwen3.5-9B-heretic-v2-i1-GGUF: Quantization
- mradermacher/Qwen3.5-9B-heretic-v2-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.