Meta's Llama 3 models are now available in Amazon Bedrock. These pre-trained and instruction-tuned large language models (LLMs) come in 8B and 70B parameter sizes, trained on over 15 trillion tokens of data.
Two new Llama 3 models are available:
- Llama 3 8B excels at text summarization, text classification, sentiment analysis, and language translation. It's suitable for limited computational power and resources, and edge devices.
- Llama 3 70B is ideal for content creation, conversational AI, language understanding, research development, and enterprise applications. It excels in various areas including text summarization and accuracy, text classification and nuance, sentiment analysis and nuance reasoning, language modeling, dialogue systems, code generation, and following instructions.
Meta is also developing Llama 3 models over 400B parameters in size, supporting multimodality, multiple languages, and a longer context window.
To use the Llama 3 models, access the Amazon Bedrock console and request access for Llama 3 8B Instruct or Llama 3 70B Instruct. You can test the models under Playgrounds, and access them using AWS CLI and AWS SDKs.
The Llama 3 models can be used for tasks like question answering, language translation, sentiment analysis, and more. They also support few-shot in-context learning and dialogue use cases.
