DavidAU/Qwen3-VL-8B-GLM-4.7-Flash-Heretic-Uncensored-Thinking
LoRA-style vs coder3101/Qwen3-VL-8B-Instruct-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, q_proj, up_proj, v_proj changed, in 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Norms 0/261, MLP 108/232, Attention 144/252, lm_head 0/1
3 derivatives checked
- mradermacher/Qwen3-VL-8B-GLM-4.7-Flash-Heretic-Uncensored-Thinking-GGUF: Same weights, converted (fewer layers)
- mradermacher/Qwen3-VL-8B-GLM-4.7-Flash-Heretic-Uncensored-Thinking-i1-GGUF: Quantization (fewer layers)
- MCult01/muse-qwen3vl-8b: LoRA-style
2 other repos hold byte-for-byte identical weight files.