sulpikar2/Qwen3.5-9B-Uncensored-cyber
LoRA-style vs GitMylo/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-safetensors. 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 31 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/5, MLP 96/211, Attention 32/336, other 0/1, Norms 0/221
3 derivatives checked
- mradermacher/Qwen3.5-9B-Uncensored-cyber-GGUF: Same weights, converted
- sulpikar2/Qwen3.5-9B-Uncensored-cyber-v3: LoRA-style
- sulpikar2/Qwen3.5-9B-Uncensored-cyber-v2: LoRA-style