An end-to-end solution leveraging open-source LLMs to generate a Q&A dataset for fine-tuning smaller and faster models and building RAG applications.
The Benchmarking AI Starter Kit offers functionality to evaluate different LLMs available on SambaStudio or SambaNova Cloud whether Llama 2 or Llama 3 from Meta, Mistral, or other in-house optimized models.
By integrating SambaNova Cloud's state-of-the-art Llama 3.1 405B model with Continue, we are transforming the way developers engage with their code.
In this post, we explore the strategic considerations and decision-making processes that can help you create impactful AI solutions.
While LLM-as-a-Judge offers a favorable alternative to human evaluations, closed source LLMs impose some limitations with this evaluation framework.
Raghu Prabhakar, Ram Sivaramakrishnan, Darshan Gandhi, Yun Du, Mingran Wang, Xiangyu Song, Kejie Zhang, Tianren Gao, Angela Wang, Karen Li, Yongning Sheng, Joshua Brot, Denis Sokolov, Apurv Vivek, Calvin Leung, Arjun Sabnis, Jiayu Bai, Tuowen Zhao, Mark Gottscho, David Jackson, Mark Luttrell, Manish K. Shah, Edison Chen, Kaizhao Liang, Swayambhoo Jain, Urmish Thakker, Dawei Huang, Sumti Jairath, Kevin J. Brown, Kunle Olukotun
Etash Guha
Published at UAI 2024
Etash Guha
Published at ICLR 2024
Etash Guha
Published at ICLR 2024
Etash Guha
Published at ICLR 2024
Kaizhao Liang
Presented at ICLR 2024
Etash Guha
Presented at Regulatable ML Workshop@NeurIPS 2023
Fenglu Hong, Bo Li, Changran Hu, Edison Chen
Presented at Foundation Models for Decision Making @NeurIPS 2023
Zolstan Csaki, Urmish Thakker
Presented at The 3rd NeurIPS Workshop on Efficient Natural Language and Speech Processing (ENLSP)
Darshan Gandhi, Urmish Thakker, Raghu Prabhakar
Presented at ICLR 2023 Workshop on Sparsity in Neural Networks
Kaizhao Liang
Presented at ICLR 2022
Urmish Thakker
Presented at ICLR 2022
Urmish Thakker
Presented at ACL 2022
Urmish Thakker
Presented at NeurIPS 2021
Kaizhao Liang
Presented at The 1st WACV Workshop on Large Language and Vision Models for Autonomous Driving (LLVM-AD)
Sumti Jairath
Presented at Computing in Science & Engineering
Benjamin Glick, Arjun Sabnis, Renate Kempf, Arnav Goel, Aarti Lalwani, Guoyao Feng, and Kiran Ranganath
Presented at ROSS Workshop, SC 2023
Edison Chen, Dawei Huang, Mingran Wang, Bowen Yang, Jinuk Luke Shin, Changran Hu, Bo Li, Raghu Prabhakar, Gao Deng, Yongning Sheng, Sihua Fu, Lu Yuan, Tian Zhao, Yun Du, Chen Liu, Jun Yang, Viren Shah, Venkat Srinivasan, Sumti Jairath
Presented at CICC 2023
Raghu Prabhakar, Jinuk Luke Shin, Sumti Jairath
Presented at ISSCC 2022
Raghu Prabhakar, Sumti Jairath
Presented at HotChips 2022