The scope of this repo is to provide an end-to-end example for using HuggingFace Flan T5 XXL model on AWS by using Amazon SageMaker Real-Time Endpoint, Amazon Comprehend, and Amazon Translate for managing multi-language inputs.
- Deploy FLAN-T5 XXL on Amazon SageMaker
- Create Your Own Large Language Model Playground in SageMaker Studio
- Architect personalized generative AI SaaS applications on Amazon SageMaker
- notebook: Use Amazon SageMaker Studio Notebooks for testing the end-to-end solution in the notebook Deploy-LLM-Model
- project: Automate the creation of an MLOps Pipeline for Model deployment by using SageMaker Project
- Run Deploy-LLM-Model
- Run the streamlit app
streamlit run flan-t5-playground.py --server.port 6006
Please refer to the instructions