Llama-3_3-Nemotron-Super-49B-GenRM

Home/Models/nvidia/Llama-3_3-Nemotron-Super-49B-GenRM

nvidia/Llama-3_3-Nemotron-Super-49B-GenRM

kind: original
quant: bf16 (16-bit)
family: llama
modality: text-generation
root model: nvidia/Llama-3_3-Nemotron-Super-49B-v1
provider: nvidia
license: other
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 104
likes: 19
created: —
last modified: 2025-06-26T18:07:35+00:00 (2025)
huggingface: https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-GenRM
tags: transformerssafetensorsnemotron-nastext-generationnvidiallama3.3conversationalcustom_codeendataset:nvidia/HelpSteer3arxiv:2505.11475arxiv:2410.01257arxiv:2310.05344arxiv:2311.09528arxiv:2406.08673arxiv:2505.00949arxiv:2410.16184base_model:nvidia/Llama-3_3-Nemotron-Super-49B-v1base_model:finetune:nvidia/Llama-3_3-Nemotron-Super-49B-v1license:otherregion:us

benchmark	category	score	context	conf	evidence
MATH	math	91.9		low	`\| [Llama-3_3-Nemotron-Super-49B-GenRM-Multilingual](https://huggingface.co/nvidia/Llama-3_3-Nemotron-Super-49B-GenRM-Multilingual) \| 77.2 \| 91.9 \| 74.7 \| 92.9 \| 90.7 \| 86.7`

none scraped.