blascotobasco/Qwen3-Next-480E-Abliterated-Instruct
LoRA-style vs Qwen/Qwen3-Next-80B-A3B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, o_proj, out_proj, up_proj changed, in 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/2, Norms 0/163, Attention 48/268, MLP 2171/2375, lm_head 0/1, other 0/1
2 derivatives checked
- mradermacher/Qwen3-Next-480E-Abliterated-Instruct-i1-GGUF: Quantization
- mradermacher/Qwen3-Next-480E-Abliterated-Instruct-GGUF: Quantization