yotisstudios/RaifuWars-Warrior-Qwen3VL-4B-v2
LoRA-style vs huihui-ai/Huihui-Qwen3-VL-4B-Instruct-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 0/4, Norms 0/249, MLP 108/220, Attention 144/240
1 derivatives checked
- mradermacher/RaifuWars-Warrior-Qwen3VL-4B-v2-GGUF: Same weights, converted (fewer layers)