-
Meta
- Menlo Park
- https://astonzhang.com/
- @astonzhangAZ
Stars
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
《动手学深度学习》:面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
The simplest, fastest repository for training/finetuning medium-sized GPTs.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
State-of-the-art 2D and 3D Face Analysis Project
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
PyTorch implementations of Generative Adversarial Networks.
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Python package built to ease deep learning on graph, on top of existing DL frameworks.
Fast and Accurate ML in 3 Lines of Code
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
Utilities intended for use with Llama models.
Probabilistic time series modeling in Python
Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)
Evolutionary Scale Modeling (esm): Pretrained language models for proteins
A modular RL library to fine-tune language models to human preferences
Pre-trained word vectors of 30+ languages
800,000 step-level correctness labels on LLM solutions to MATH problems