Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

A reading list on LLM based Synthetic Data Generation 🔥

The Memory layer for AI Agents

[ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

Schedule-Free Optimization in PyTorch

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

Awesome-LLM: a curated list of Large Language Model

A lightweight, dependency-free Python library (and command-line utility) for downloading YouTube Videos.

Official code of the paper 4D-OR: Semantic Scene Graphs for OR Domain Modeling accepted at MICCAI 2022. This repo includes both the dataset and our code.

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

State-of-the-Art Text Embeddings

A proof-of-concept project that showcases the potential for using small, locally trainable LLMs to create next-generation documentation tools.

Vision Transformers are Parameter-Efficient Audio-Visual Learners

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

LLM finetuned for medical question answering

The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement …

KenLM: Faster and Smaller Language Model Queries

HuggingSound: A toolkit for speech-related tasks based on Hugging Face's tools

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

Aligning pretrained language models with instruction data generated by themselves.

Voice models for Mimic 3 text to speech system

The simplest, fastest repository for training/finetuning medium-sized GPTs.

🔊 Text-Prompted Generative Audio Model

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

Code and documentation to train Stanford's Alpaca models, and generate the data.