pankajmathur/Mimma-3-1b_v2
LoRA-style vs google/gemma-3-1b-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 26 of 26 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/157, MLP 78/78, Attention 104/104
2 derivatives checked
- mradermacher/Mimma-3-1b_v2-i1-GGUF: Quantization
- mradermacher/Mimma-3-1b_v2-GGUF: Same weights, converted