Subskrybuj, aby otrzymywać powiadomienia na temat nowych wpisów:

Meta Llama 3.1 now available on Workers AI

2024-07-23

2 min czytania
Ten post jest również dostępny w następującym języku: English.
Meta Llama 3.1 now available on Workers AI

At Cloudflare, we’re big supporters of the open-source community – and that extends to our approach for Workers AI models as well. Our strategy for our Cloudflare AI products is to provide a top-notch developer experience and toolkit that can help people build applications with open-source models.

We’re excited to be one of Meta’s launch partners to make their newest Llama 3.1 8B model available to all Workers AI users on Day 1. You can run their latest model by simply swapping out your model ID to @cf/meta/llama-3.1-8b-instruct or test out the model on our Workers AI Playground. Llama 3.1 8B is free to use on Workers AI until the model graduates out of beta.

Meta’s Llama collection of models have consistently shown high-quality performance in areas like general knowledge, steerability, math, tool use, and multilingual translation. Workers AI is excited to continue to distribute and serve the Llama collection of models on our serverless inference platform, powered by our globally distributed GPUs.

The Llama 3.1 model is particularly exciting, as it is released in a higher precision (bfloat16), incorporates function calling, and adds support across 8 languages. Having multilingual support built-in means that you can use Llama 3.1 to write prompts and receive responses directly in languages like English, French, German, Hindi, Italian, Portuguese, Spanish, and Thai. Expanding model understanding to more languages means that your applications have a bigger reach across the world, and it’s all possible with just one model.

const answer = await env.AI.run('@cf/meta/llama-3.1-8b-instruct', {
    stream: true,
    messages: [{
        "role": "user",
        "content": "Qu'est-ce que ç'est verlan en français?"
    }],
});

Llama 3.1 also introduces native function calling (also known as tool calls) which allows LLMs to generate structured JSON outputs which can then be fed into different APIs. This means that function calling is supported out-of-the-box, without the need for a fine-tuned variant of Llama that specializes in tool use. Having this capability built-in means that you can use one model across various tasks.

Workers AI recently announced embedded function calling, which is now usable with Meta Llama 3.1 as well. Our embedded function calling gives developers a way to run their inference tasks far more efficiently than traditional architectures, leveraging Cloudflare Workers to reduce the number of requests that need to be made manually. It also makes use of our open-source ai-utils package, which helps you orchestrate the back-and-forth requests for function calling along with other helper methods that can automatically generate tool schemas. Below is an example function call to Llama 3.1 with embedded function calling that then stores key-values in Workers KV.

const response = await runWithTools(env.AI, "@cf/meta/llama-3.1-8b-instruct", {
    messages: [{ role: "user", content: "Greet the user and ask them a question" }],
    tools: [{
        name: "Store in memory",
        description: "Store everything that the user talks about in memory as a key-value pair.",
        parameters: {
            type: "object",
            properties: {
                key: {
                    type: "string",
                    description: "The key to store the value under.",
                },
                value: {
                    type: "string",
                    description: "The value to store.",
                },
            },
            required: ["key", "value"],
        },
        function: async ({ key, value }) => {
                await env.KV.put(key, value);

                return JSON.stringify({
                    success: true,
                });
         }
    }]
})

We’re excited to see what you build with these new capabilities. As always, use of the new model should be conducted with Meta’s Acceptable Use Policy and License in mind. Take a look at our developer documentation to get started!

Chronimy całe sieci korporacyjne, pomagamy klientom sprawnie tworzyć aplikacje o skali internetowej, przyspieszamy działanie wszelkich witryn i aplikacji internetowych, zapobiegamy atakom DDoS, trzymamy hakerów z daleka oraz możemy pomóc Ci we wdrażaniu modelu Zero Trust.

Odwiedź stronę 1.1.1.1 na dowolnym urządzeniu i zacznij korzystać z naszej bezpłatnej aplikacji, dzięki której Twój Internet będzie szybszy i bezpieczniejszy.

Aby dowiedzieć się więcej o naszej misji budowania lepszego Internetu, przejdź tutaj . Jeśli interesuje Cię zmiana ścieżki kariery, sprawdź nasze wolne stanowiska.
Workers AISIWiad. o prod.Developer PlatformProgramiściOpen Source

Obserwuj nas w serwisie X

Michelle Chen|@_mchenco
Cloudflare|@cloudflare

Powiązane wpisy

09 października 2024 13:00

Improving platform resilience at Cloudflare through automation

We realized that we need a way to automatically heal our platform from an operations perspective, and designed and built a workflow orchestration platform to provide these self-healing capabilities across our global network. We explore how this has helped us to reduce the impact on our customers due to operational issues, and the rich variety of similar problems it has empowered us to solve....

08 października 2024 13:00

Cloudflare acquires Kivera to add simple, preventive cloud security to Cloudflare One

The acquisition and integration of Kivera broadens the scope of Cloudflare’s SASE platform beyond just apps, incorporating increased cloud security through proactive configuration management of cloud services. ...

27 września 2024 13:00

Our container platform is in production. It has GPUs. Here’s an early look

We’ve been working on something new — a platform for running containers across Cloudflare’s network. We already use it in production, for AI inference and more. Today we want to share an early look at how it’s built, why we built it, and how we use it ourselves. ...