Cloudflare recently announced that as one of Meta's first partners, they have launched the latest Meta-released Llama3.18B model on the Workers AI platform. This move allows developers to start using this advanced AI tool on the very first day of its release.
Llama3.1 is the latest member of Meta's Llama series models, renowned for its outstanding performance in general knowledge, controllability, mathematical operations, tool usage, and multilingual translation. The highlights of this update include: Higher accuracy: The model adopts the bfloat16 format, enhancing computational precision.
- Function calling capability: The model is equipped with built-in function calling (also known as tool calling) capabilities, allowing it to generate structured JSON outputs that can be directly used for various APIs.
- Multilingual support: The new model supports eight languages, including English, French, German, Hindi, Italian, Portuguese, Spanish, and Thai, significantly expanding its application scope.
Cloudflare emphasizes their commitment to supporting the open-source community, extending this philosophy to the Workers AI product. The company states that their goal is to provide developers with first-class development experiences and toolkits to help people build applications using open-source models.
It is worth noting that during the beta testing period, developers can use the Llama3.18B model for free. Cloudflare has also introduced an embedded function calling feature, which allows developers to run inference tasks more efficiently, reducing the number of manual requests.
Cloudflare's move not only demonstrates their support for the development of open-source AI but also provides global developers with more opportunities to explore and apply the latest AI technologies. As AI models continue to evolve, we can expect to see more innovative applications emerge.
Experience it at: https://playground.ai.cloudflare.com/