rasyosef/Mistral-NeMo-Minitron-8B-Chat
LoRA-style vs nvidia/Mistral-NeMo-Minitron-8B-Base. 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
2 derivatives checked
- mradermacher/Mistral-NeMo-Minitron-8B-Chat-i1-GGUF: Quantization
- mradermacher/Mistral-NeMo-Minitron-8B-Chat-GGUF: Same weights, converted