DavidAU/Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2
LoRA-style vs huihui-ai/Huihui-Qwen3-30B-A3B-Thinking-2507-abliterated. 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 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/193, MLP 2544/2613, Attention 192/192, lm_head 0/1
4 derivatives checked
- mradermacher/Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2-i1-GGUF: Quantization
- mradermacher/Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2-GGUF: Quantization
- kainah/Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2-Q4_K_M-GGUF: Quantization
- nrlmuojb/Qwen3-30B-A3B-Claude-4.5-Opus-High-Reasoning-2507-ABLITERATED-UNCENSORED-V2-mlx-6Bit: Quantization
2 other repos hold byte-for-byte identical weight files.