Deploy open-source LLMs on AWS in minutes — with OpenAI-compatible APIs and a powerful CLI/SDK toolkit.

Smithy code generators for Go (in development)

A lightning-fast workflow builder, it supports multimodal interaction, highly customizable extensions, and is intuitive to use even without any coding knowledge.

An Open-Sourced LLM-empowered Foundation TTS System

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

In this demo, we show two samples about deepfm distributed training on Amazon SageMaker, one is based on Tensorflow Parameter Server on CPU and the other one is based on Horovod on GPU.

LLM Frontend for Power Users.

Multimodal Agent based on Bedrock, AST(Transcribe), TTS(Polly)

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.

This repository is part of a blog post that guides users through creating a visual search application using Amazon SageMaker and Amazon Elasticsearch service

Drag and Drop Website Builder and CMS with E-commerce

A TensorFlow Serving solution for use in SageMaker.

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

CLI proof of concept - live translation with polly