Jun 14, 06:18 PM

NVIDIA Unveils Ambitious 340B Model, Surpasses Llama-3-70b

NVIDIA has unveiled its most ambitious project to date, releasing a family of open-source models aimed at generating synthetic data for building other large language models (LLMs). The flagship model, named '340B', was tested under the codename 'june-chatbot' and has demonstrated impressive performance, surpassing Llama-3-70b across challenging benchmarks like Arena-Hard-Auto. This release marks a significant milestone in the field of artificial intelligence and robotics, potentially easing concerns about 'model collapse' and pushing the boundaries of future technology.

#NVIDIA

Written with ChatGPT (GPT-4o).

Sources

chrisrohlf@chrisrohlf
2 years ago
Woah! Did not expect to see NVIDIA releasing an open model for the purpose of generating synthetic data to build other LLMs. Perhaps ‘model collapse’ isn’t as close as feared? https://t.co/qXJlSCCukr
lmarena.ai@lmarena_ai
2 years ago
Congrats @nvidia on the exciting 340B model release! The model was tested under the codename "june-chatbot" and is now coming out of stealth with impressive performance, surpassing Llama-3-70b across hard benchmarks like Arena-Hard-Auto. The new best open model? Come play with… https://t.co/j5aztYhSvh https://t.co/fPLJeuvDHc
Invisibility@invisibilityinc
2 years ago
Nvidia graphics card announcement in 2020 🤯 imagine running ChatGPT on this https://t.co/4ofbSDqDYH

NVIDIA Unveils Ambitious 340B Model, Surpasses Llama-3-70b

Sources

Additional media

Similar Stories