Aimin12/Qwen3-4B-Thinking-2507-Distill-Claude-Opus-4.6-Reasoning-Abliterated
LoRA-style vs huihui-ai/Huihui-Qwen3-4B-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 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 108/108, Attention 144/144
3 derivatives checked
- mradermacher/Qwen3-4B-Thinking-2507-Distill-Claude-Opus-4.6-Reasoning-Abliterated-i1-GGUF: Quantization
- mradermacher/Qwen3-4B-Thinking-2507-Distill-Claude-Opus-4.6-Reasoning-Abliterated-GGUF: Same weights, converted
- ZeroXClem/Qwen3-4B-Wrist-On-Hermes: Full fine-tune