nvidia/Llama-3_3-Nemotron-Super-49B-GenRM
Full fine-tune vs nvidia/Llama-3_3-Nemotron-Super-49B-v1. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 78/130, MLP 240/240, Attention 196/196, lm_head 1/1
2 derivatives checked
- mradermacher/Llama-3_3-Nemotron-Super-49B-GenRM-i1-GGUF: Quantization
- mradermacher/Llama-3_3-Nemotron-Super-49B-GenRM-GGUF: Quantization