trohrbaugh/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
20 derivatives checked
- DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED: LoRA-style
- AIImageStudio/Qwen3.5-9b-heretic-v2-GGUF: Quantization
- filvyb/Qwen3.5-9B-heretic-v2-GGUF: Same weights, converted
- Crownelius/Crow-9B-HERETIC-4.6: LoRA-style
- Atonelia/Qwen3.5-Sydney-9B-GGUF: Quantization
- DavidAU/Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED: LoRA-style
- Babsie/Crow_Qwen9B_OpusUCH: LoRA-style
- llmStra33/Qwen3.5-9B-heretic-v2-Q4_K_M-GGUF: Quantization
- Kaleto/Qwen3.5-9B-heretic-v2-NVFP4-MTP: Quantization
- Atonelia/Qwen3.5-Sydney-9B-think-GGUF: Quantization
- DavidAU/Qwen3.5-9B-Claude-4.6-OS-HERETIC-UNCENSORED-INSTRUCT: LoRA-style
- Kaiserg3/Crow-9B-HERETIC-4.6: LoRA-style
- DavidAU/Qwen3.5-13B-Deckard-Heretic-Uncensored-Thinking: Partial fine-tune
- modinformal/Crow-9B-Opus-4.6-Distill-Heretic_Qwen3.5: LoRA-style
- Crowfeather/Crow-9B-Opus-4.6-Distill-Heretic_Qwen3.5: LoRA-style
- DavidAU/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING: LoRA-style
- DavidAU/Qwen3.5-9B-Star-Trek-TNG-DS9-Heretic-Uncensored-Thinking: LoRA-style
- DavidAU/Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking: LoRA-style
- DavidAU/Qwen3.5-9B-Deckard-Claude-DIMOE-Uncensored-Heretic-Thinking: LoRA-style
- zswll2/Qwen3.5-9B-Claude-4.6-HighIQ-THINKING-HERETIC-UNCENSORED: LoRA-style
1 other repos hold byte-for-byte identical weight files.