Fast and cost-effective LLaMA 2 fine-tuning with AWS Trainium
AWS Machine Learning
OCTOBER 5, 2023
These models can be used for question answering, summarization, translation, and more in applications such as conversational agents for customer support, content creation for marketing, and coding assistants. Compared to Llama 1, Llama 2 doubles context length from 2,000 to 4,000, and uses grouped-query attention (only for 70B).
Let's personalize your content