nbeerbower/mistral-nemo-gutenberg-12B-v3
LoRA-style vs intervitens/mini-magnum-12b-v1.1. 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 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 120/120, Attention 160/160, lm_head 0/1
4 derivatives checked
- mradermacher/mistral-nemo-gutenberg-12B-v3-i1-GGUF: Quantization
- QuantFactory/mistral-nemo-cc-12B-GGUF: Quantization
- mradermacher/mistral-nemo-gutenberg-12B-v3-GGUF: Quantization
- nbeerbower/mistral-nemo-cc-12B: LoRA-style