dipta007/VCInspector-3B
LoRA-style vs Qwen/Qwen2.5-VL-3B-Instruct. 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 0/2, Norms 0/138, MLP 108/304, Attention 144/380
2 derivatives checked
- mradermacher/VCInspector-3B-i1-GGUF: Quantization (fewer layers)
- mradermacher/VCInspector-3B-GGUF: Same weights, converted (fewer layers)