soob3123/GrayLine-Gemma3-12B
LoRA-style vs google/gemma-3-12b-it-qat-q4_0-unquantized. 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 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Norms 0/400, MLP 144/252, Attention 192/408, other 0/1
2 derivatives checked
- mradermacher/GrayLine-Gemma3-12B-i1-GGUF: Quantization (fewer layers)
- mradermacher/GrayLine-Gemma3-12B-GGUF: Quantization (fewer layers)