Meta Llama in Amazon Bedrock

Build the future of AI with Meta

Get started with Llama in Amazon Bedrock

Introducing Meta Llama 3

Llama 3 8B

Llama 3 8B is ideal for limited computational power and resources, faster training times, and edge devices. The model excels at text summarization, text classification, sentiment analysis, and language translation.
Llama 3 70B

Llama 3 70B is ideal for content creation, conversational AI, language understanding, research development, and enterprise applications. The model excels at text summarization and accuracy, text classification and nuance, sentiment analysis and nuance reasoning, language modeling, dialogue systems, code generation, and following instructions.

Benefits

Over 1 million human annotations

The fine-tuned model, Llama Chat, leverages publicly available instruction datasets and over 1 million human annotations.

Pretrained on trillions of tokens

Llama models are trained on trillions of tokens from online public data sources to better comprehend language intricacies.

Over 1,000 hours of red-teaming

The fine-tuned model has over 1,000 hours of red-teaming and annotation effort to ensure safety with model performance.

Zero infrastructure management

Amazon Bedrock is the ﬁrst public cloud service to oﬀer a fully managed API for Llama. Organizations of all sizes can access Llama 2 models in Amazon Bedrock without having to manage the underlying infrastructure.

Meet Llama

Amazon Bedrock is the first public cloud service to offer a fully managed API for Llama, Meta’s next-generation large language model (LLM). Now, organizations of all sizes can access Llama models in Amazon Bedrock without having to manage the underlying infrastructure. This means you can focus on what you do best—building your AI applications. The partnership between Meta and Amazon signifies collective generative AI innovation. Meta and Amazon are working together to push the boundaries of what's possible.

Use cases

Meta's Llama models are accessible large language models designed for developers, researchers, and businesses to build, experiment, and responsibly scale generative AI ideas. Llama is an integral part of a foundational system that enables innovation in the global community.

Model versions

Llama 3 8B

Ideal for limited computational power and resources, faster training times, and edge devices.

Max tokens: 8K

Languages: English

Supported use cases: Text summarization, text classification, sentiment analysis, and language translation

Llama 3 70B

Ideal for content creation, conversational AI, language understanding, research development, and enterprise applications.

Max tokens: 8K

Languages: English

Supported use cases: Text summarization and accuracy, text classification and nuance, sentiment analysis and nuance reasoning, language modeling, dialogue systems, code generation, and following instructions.

Llama 2 13B

Fine-tuned model in the parameter size of 13B. Suitable for smaller-scale tasks such as text classification, sentiment analysis, and language translation.

Max tokens: 4K

Languages: English

Supported use cases: Assistant-like chat