DavidAU/Qwen3.5-27B-Deckard-PKD-Heretic-Uncensored-Thinking
LoRA-style vs coder3101/Qwen3.5-27B-heretic. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, out_proj, q_proj, up_proj, v_proj changed, in 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 0/319, Attention 112/556, MLP 192/304
6 derivatives checked
- mradermacher/Qwen3.5-27B-Deckard-PKD-Heretic-Uncensored-Thinking-i1-GGUF: Quantization
- mradermacher/Qwen3.5-27B-Deckard-PKD-Heretic-Uncensored-Thinking-GGUF: Quantization
- DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking: Partial fine-tune
- DavidAU/Qwen3.5-21B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking: Partial fine-tune
- DavidAU/Qwen3.5-21B-GLM-4.7-Flash-Heretic-Uncensored-Thinking: Partial fine-tune
- DavidAU/Qwen3.5-21B-GLM-4.7-Flash-Deckard-Heretic-Uncensored-Thinking: Partial fine-tune