kai-os/Grug-12B
LoRA-style vs google/gemma-4-12B-it. 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 0/12, Norms 0/289, other 0/48, MLP 144/144, Attention 184/184
5 derivatives checked
- bartowski/kai-os_Grug-12B-GGUF: Same weights, converted
- mradermacher/Grug-12B-i1-GGUF: Quantization
- mradermacher/Grug-12B-GGUF: Quantization
- liodon-ai/Grug-12B-imatrix-GGUF: Quantization
- kai-os/Grug-12B-GGUF: Quantization