DavidAU/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness
Partial fine-tune (fewer layers) vs trohrbaugh/Qwen3.6-27B-heretic-ara. DavidAU/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness matches part of trohrbaugh/Qwen3.6-27B-heretic-ara (548 of its 1199 tensors; the rest of trohrbaugh/Qwen3.6-27B-heretic-ara has no counterpart). On the shared part: Partial change: 67% of the weights changed (attention, mlp, norms), in 16 of 27 layers.
Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 39/163, Attention 103/220, MLP 48/160
4 derivatives checked
- Blasserman/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-Q4_K_M-GGUF: Quantization
- filvyb/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-GGUF: Same weights, converted
- KryptykAngel/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-GGUF: Same weights, converted
- Uwes1980/Qwen3.6-9B-Heretic-Uncensored-Thinking-Sweet-Madness-GGUF: Same weights, converted
4 other repos hold byte-for-byte identical weight files.