The Llama 3.3 70B model from Meta is now available in Amazon SageMaker JumpStart, offering a cost-effective and efficient option for large language model deployments with high performance.
This model was built using a new Smaug recipe for improving performance on real world multi-turn conversations applied to meta-llama/Meta-Llama-3-70B-Instruct.
The model outperforms Llama-3-70B-Instruct substantially, and is on par with GPT-4-Turbo, on MT-Bench (see below).
