nvidia/Llama-3_3-Nemotron-Super-49B-GenRM-Multilingual
Full fine-tune vs nvidia/Llama-3_3-Nemotron-Super-49B-v1. Fine-tune: 98% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 0/1, Norms 72/130, MLP 240/240, Attention 196/196, lm_head 1/1
2 derivatives checked
- bartowski/nvidia_Llama-3_3-Nemotron-Super-49B-GenRM-Multilingual-GGUF: Same weights, converted
- DevQuasar/nvidia.Llama-3_3-Nemotron-Super-49B-GenRM-Multilingual-GGUF: Same weights, converted