HagalazAI/CyberDolphin-2.9.3-mistral-nemo-12b
LoRA-style vs dphn/dolphin-2.9.3-mistral-nemo-12b. 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 120/120, Attention 160/160
1 derivatives checked
- HagalazAI/CyberDolphin-2.9.3-mistral-nemo-12b-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.