nicoboss/dolphin-2.9.3-mistral-nemo-12b-llamacppfixed
LoRA-style vs mistralai/Mistral-Nemo-Base-2407. 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: Norms 0/81, MLP 60/120, Attention 80/160
2 derivatives checked
- mradermacher/dolphin-2.9.3-mistral-nemo-12b-llamacppfixed-GGUF: Quantization
- mradermacher/dolphin-2.9.3-mistral-nemo-12b-llamacppfixed-i1-GGUF: Quantization
2 other repos hold byte-for-byte identical weight files.