SSMs Collection A collection of Mamba-2-based research models with 8B parameters trained on 3.5T tokens for comparison with Transformers. • 5 items • Updated 22 days ago • 25
NV-Embed Collection NV-Embed is a generalist embedding model that ranks No. 1 on MTEB benchmark encompassing retrieval, reranking, classification, clustering, STS tasks • 2 items • Updated 22 days ago • 9
RLHF Collection A collection of models trained with Reinforcement Learning from Human Feedback (RLHF). • 4 items • Updated 22 days ago • 4
OpenMath Collection A collection of models and datasets introduced in "OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset" • 15 items • Updated 22 days ago • 37
InstructRetro Collection InstructRetro is an autoregressive decoder-only language model (LM) with retrieval-augmented pretraining and instruction tuning. • 4 items • Updated 22 days ago • 9
Canary Collection A collection of multilingual and multitask speech to text models from NVIDIA NeMo 🐤 • 1 item • Updated 22 days ago • 17
Parakeet Collection NeMo Parakeet ASR Models attain strong speech recognition accuracy while being efficient for inference. Available in CTC and RNN-Transducer variants. • 8 items • Updated 22 days ago • 20
SteerLM Collection A collection of models and datasets relating to SteerLM and HelpSteer. • 7 items • Updated 22 days ago • 14
Nemotron 3 8B Collection The Nemotron 3 8B Family of models is optimized for building production-ready generative AI applications for the enterprise. • 5 items • Updated 22 days ago • 44