E27085921/HIKARI-Subaru-8B-SkinGroup
LoRA-style vs Qwen/Qwen3-VL-8B-Thinking. 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 0/261, MLP 108/232, Attention 144/252, lm_head 0/1
1 derivatives checked
- mradermacher/HIKARI-Subaru-8B-SkinGroup-GGUF: Same weights, converted (fewer layers)