Andycurrent/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive
LoRA-style vs Qwen/Qwen3.5-4B. Andycurrent/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive is a GGUF (BF16) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, o_proj, up_proj changed, in 16 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, MLP 32/96, Norms 0/81, Attention 3/32