Clone a voice in 5 seconds to generate arbitrary speech in real-time

The uncompromising Python code formatter

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

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Universal LLM Deployment Engine with ML Compilation

Python package built to ease deep learning on graph, on top of existing DL frameworks.

Open deep learning compiler stack for cpu, gpu and specialized accelerators

Hackable and optimized Transformers building blocks, supporting a composable construction.

Fast and Accurate ML in 3 Lines of Code

👷 Build images with images

Probabilistic time series modeling in Python

Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate, LanceDB).

NLP made easy

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image …

Returns latest research results by crawling arxiv papers and summarizing abstracts. Helps you stay afloat with so many new papers everyday.

Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation (SIGGRAPH Asia 2021)

Make Llama2 use Code Execution, Debug, Save Code, Reuse it, Access to Internet

Train machine learning models within a 🐳 Docker container using 🧠 Amazon SageMaker.

data cleaning and curation for unstructured text

LLM-based text extraction from unstructured data like PDFs, Words and HTMLs. Transform and cluster the text into your desired format. Less information loss, more interpretation, and faster R&D!

PyTorch codebase for zero-shot dialog generation SIGDIAL 2018, It is released by Tiancheng Zhao (Tony) from Dialog Research Center, LTI, CMU

LLM Testing SDK that helps you write and run tests to monitor your LLM app in production

Accurate, private and configurable document retrieval LLM

OpenAI Whisper for edge devices

Fine-tuning and serving LLMs on any cloud

cluster/scheduler health monitoring for GPU jobs on k8s

Examples showing use of NGC containers and models withing Amazon SageMaker

A simple Pure Python/PyTorch performance daemon for training workloads