Reward Models Collection Nemotron reward models. For use in RLHF pipelines and LLM-as-a-Judge • 8 items • Updated 1 day ago • 10
nvidia/Llama-3_3-Nemotron-Super-49B-GenRM-Multilingual Text Generation • 50B • Updated 8 days ago • 7 • 5
nvidia/llama-nemoretriever-colembed-3b-v1 Visual Document Retrieval • 4B • Updated 7 days ago • 118 • 21
ERNIE 4.5 Collection collection of ERNIE 4.5 models. "-Paddle" models use PaddlePaddle weights, while "-PT" models use Transformer-style PyTorch weights. • 23 items • Updated 1 day ago • 132