Amazon Web Services (AWS) has introduced two new foundation models in Amazon SageMaker JumpStart, namely Code Llama and Mistral 7B.
Code Llama, a variant of Meta’s Llama 2 model, is available in three forms: base, Python, and Instruct, each in three different model sizes for code generation and code infilling tasks.
Mistral 7B is a language model consisting of seven billion parameters, intended for general text generation alongside code generation. Two versions of Mistral 7B are available: base and Instruct.
By using this site, you agree to allow SPEEDA Edge and our partners to use cookies for analytics and personalization. Visit our privacy policy for more information about our data collection practices.