prithivMLmods/OneDecision-VisionGuard-9B-SFT
LoRA-style vs Qwen/Qwen3.5-9B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, in_proj_a, in_proj_b, in_proj_qkv, in_proj_z, k_proj, linear_fc1, linear_fc2, o_proj, out_proj, proj, q_proj, qkv, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/4, MLP 149/208, Attention 206/332, Norms 0/215
2 derivatives checked
- prithivMLmods/OneDecision-VisionGuard-9B-SFT-GGUF: Same weights, converted
- mradermacher/OneDecision-VisionGuard-9B-SFT-GGUF: Same weights, converted