Llama 3 Unveiled: Meta’s Improved Open-Source Language Models and Integration into AI Assistant

Meta has unveiled the latest generation of its open-source large language model, Llama 3, with two text-based models trained with 8B and 70B parameters. These models offer improved reasoning capabilities and are integrated into the Meta AI assistant, positioning them as best-in-class open source models. The company aims to continue driving innovation in AI across various applications, tools, and optimizations.

Initially anticipated for May, the release of Llama 3 was delayed but now features two state-of-the-art models trained with massive data sets. The models have undergone rigorous filtering processes to ensure data quality and reliability. Additionally, more than 5% of the pre-training data set includes information in languages other than English, preparing for upcoming multilingual use cases.

To ensure responsible use of Llama 3, Meta has introduced resources like Llama Guard 2, Code Shield, and CyberSecEval 2 to promote safe interactions with the models. The latest Llama 3 models have been integrated into the Meta AI assistant across platforms like Facebook, Instagram, WhatsApp, and Messenger. Users can download these models and soon access them on various platforms including Amazon Web Services, Google Cloud, IBM WatsonX, Microsoft Azure, and more.

Meta plans to introduce new capabilities such as longer context windows, additional model sizes, and improved performance for Llama 3 in the coming months. Research work on this model will also be shared by the company as it continues to drive innovation in AI across various applications and tools.