DavidAU/Qwen3.5-9B-Star-Trek-TNG-DS9-Heretic-Uncensored-Thinking
LoRA-style vs trohrbaugh/Qwen3.5-9B-heretic-v2. 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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 0/215, Attention 56/332, MLP 96/208
3 derivatives checked
- mradermacher/Qwen3.5-9B-Star-Trek-TNG-DS9-Heretic-Uncensored-Thinking-i1-GGUF: Quantization
- DavidAU/Qwen3.5-9B-Star-Trek-TNG-DS9-Heretic-Uncensored-Thinking-MAX-NEOCODE-GGUF: Same weights, converted
- mradermacher/Qwen3.5-9B-Star-Trek-TNG-DS9-Heretic-Uncensored-Thinking-GGUF: Same weights, converted