Sources
Loading...
Additional media
Loading...
DeepNewz, mobile.
People-sourced. AI-powered. Unbiased News.
Arcee AI has launched its flagship model, SuperNova, a 70 billion parameter language model designed for enterprise deployment. SuperNova, which is a distilled version of Meta's Llama 3.1 405B, leverages advanced post-training techniques including offline knowledge distillation, reinforcement learning from human feedback (RLHF), and model merging. The model aims to provide a powerful and customizable alternative to ChatGPT Enterprise, offering state-of-the-art instruction-following capabilities. SuperNova is now available on the AWS Marketplace, allowing customers to deploy and run the model on Amazon SageMaker. Additionally, Arcee AI has listed other models such as Llama Spark 8B and Arcee Nova 72B on the AWS Marketplace.
Arcee-SuperNova is another cool example of applying model distillation on Llama-3.1-405B. Key takeaways: - They use a level logit compression technique to overcome the hardware requirements needed to distill such a big model. - Took about 5 days to distill into… https://t.co/zdOeHGBQmG
First distilled Llama 3.1 released by @arcee_ai! 🦙 SuperNova is a distilled reasoning Llama 3.1 70B & 8B! 👀 Arcee distilled @AIatMeta Llama 3.1 405B using offline knowledge distillation and combined it with RLHF and model merging to create new #1 open LLMs. SuperNova 70B is… https://t.co/ZoWmZoMR3Q
First distilled Llama 3.1 released by @arcee_ai! 🦙 SuperNova is a distilled reasoning Llama 3.1 70B & 8B! 👀 @arcee_ai distilled @AIatMeta Llama 3.1 405B using offline knowledge distillation and combined it with RLHF and model merging to create new #1 open LLMs. SuperNova 70B is…
