NVIDIA Nemotron Nano V2 VL
NVIDIA Nemotron Nano V2 VL
November 6, 2025
저자: NVIDIA, Amala Sanjay Deshmukh, Kateryna Chumachenko, Tuomas Rintamaki, Matthieu Le, Tyler Poon, Danial Mohseni Taheri, Ilia Karmanov, Guilin Liu, Jarno Seppanen, Guo Chen, Karan Sapra, Zhiding Yu, Adi Renduchintala, Charles Wang, Peter Jin, Arushi Goel, Mike Ranzinger, Lukas Voegtle, Philipp Fischer, Timo Roman, Wei Ping, Boxin Wang, Zhuolin Yang, Nayeon Lee, Shaokun Zhang, Fuxiao Liu, Zhiqi Li, Di Zhang, Greg Heinrich, Hongxu, Yin, Song Han, Pavlo Molchanov, Parth Mannan, Yao Xu, Jane Polak Scowcroft, Tom Balough, Subhashree Radhakrishnan, Paris Zhang, Sean Cha, Ratnesh Kumar, Zaid Pervaiz Bhat, Jian Zhang, Darragh Hanley, Pritam Biswas, Jesse Oliver, Kevin Vasques, Roger Waleffe, Duncan Riach, Oluwatobi Olabiyi, Ameya Sunil Mahabaleshwarkar, Bilal Kartal, Pritam Gundecha, Khanh Nguyen, Alexandre Milesi, Eugene Khvedchenia, Ran Zilberstein, Ofri Masad, Natan Bagrov, Nave Assaf, Tomer Asida, Daniel Afrimi, Amit Zuker, Netanel Haber, Zhiyu Cheng, Jingyu, Xin, Di, Wu, Nik Spirin, Maryam Moosaei, Roman Ageev, Vanshil Atul Shah, Yuting Wu, Daniel Korzekwa, Unnikrishnan Kizhakkemadam Sreekumar, Wanli Jiang, Padmavathy Subramanian, Alejandra Rico, Sandip Bhaskar, Saeid Motiian, Kedi Wu, Annie Surla, Chia-Chih Chen, Hayden Wolff, Matthew Feinberg, Melissa Corpuz, Marek Wawrzos, Eileen Long, Aastha Jhunjhunwala, Paul Hendricks, Farzan Memarian, Benika Hall, Xin-Yu Wang, David Mosallanezhad, Soumye Singhal, Luis Vega, Katherine Cheung, Krzysztof Pawelec, Michael Evans, Katherine Luna, Jie Lou, Erick Galinkin, Akshay Hazare, Kaustubh Purandare, Ann Guan, Anna Warno, Chen Cui, Yoshi Suhara, Shibani Likhite, Seph Mard, Meredith Price, Laya Sleiman, Saori Kaji, Udi Karpas, Kari Briski, Joey Conway, Michael Lightstone, Jan Kautz, Mohammad Shoeybi, Mostofa Patwary, Jonathen Cohen, Oleksii Kuchaiev, Andrew Tao, Bryan Catanzaro
cs.AI
초록
우리는 강력한 실제 문서 이해, 장편 비디오 이해 및 추론 과제를 위해 설계된 Nemotron 비전-언어 시리즈의 최신 모델인 Nemotron Nano V2 VL을 소개합니다. Nemotron Nano V2 VL은 모델 아키텍처, 데이터셋 및 학습 방법론의 주요 개선을 통해 모든 비전 및 텍스트 영역에서 이전 모델인 Llama-3.1-Nemotron-Nano-VL-8B 대비 상당한 향상을 제공합니다. Nemotron Nano V2 VL은 하이브리드 Mamba-Transformer LLM인 Nemotron Nano V2와 혁신적인 토큰 축소 기술을 기반으로 하여 장문 문서 및 비디오 시나리오에서 더 높은 추론 처리량을 달성합니다. BF16, FP8 및 FP4 형식의 모델 체크포인트와 데이터셋, 방법론 및 학습 코드의 상당 부분을 공개합니다.
English
We introduce Nemotron Nano V2 VL, the latest model of the Nemotron
vision-language series designed for strong real-world document understanding,
long video comprehension, and reasoning tasks. Nemotron Nano V2 VL delivers
significant improvements over our previous model,
Llama-3.1-Nemotron-Nano-VL-8B, across all vision and text domains through major
enhancements in model architecture, datasets, and training recipes. Nemotron
Nano V2 VL builds on Nemotron Nano V2, a hybrid Mamba-Transformer LLM, and
innovative token reduction techniques to achieve higher inference throughput in
long document and video scenarios. We are releasing model checkpoints in BF16,
FP8, and FP4 formats and sharing large parts of our datasets, recipes and
training code.