Next-Token Prediction is All You Need

Whisper realtime streaming for long speech-to-text transcription and translation

ViT Prisma is a mechanistic interpretability library for Vision Transformers (ViTs).

Pipeline parallel implementations for LLMs

A fast multimodal LLM for real-time voice

Joint speech-language model - respond directly to audio!

Joint speech-language model - respond directly to audio!

Website for hosting the Open Foundation Models Cheat Sheet.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Mass-editing thousands of facts into a transformer memory (ICLR 2023)

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Erasing concepts from neural representations with provable guarantees

Examples and guides for using the OpenAI API

A ChatGPT plugin that allows you to load and edit your local files in a controlled way, as well as run any Python, JavaScript, and bash script.

ImageBind One Embedding Space to Bind Them All

Unsupervised Speech Decomposition Via Triple Information Bottleneck

✨ Build AI interfaces that spark joy

A dataset featuring diverse dialogues between two ChatGPT (gpt-3.5-turbo) instances with system messages written by GPT-4. Covering various contexts and tasks (task-oriented dialogue systems, abstr…

Neural network-based singing voice synthesis library for research

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code

Diffusers Stable Diffusion as a Cog model

A collection of resources and papers on Diffusion Models

CMU Lecture: Machine Learning In Production / AI Engineering / Software Engineering for AI-Enabled Systems (SE4AI)

Software Engineering for AI/ML -- An Annotated Bibliography

A python Library to easily use & configure a suite of services provided by Lethical.AI (https://lethical.ai)

Download, Install, Update