OCR & Document Extraction using vision models

LLM inference in C/C++

LLM training in simple, raw C/CUDA

[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

Implementation of Nougat Neural Optical Understanding for Academic Documents

Let us control diffusion models!

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

Karras et al. (2022) diffusion models for PyTorch

A list of awesome Machine Translation frameworks, libraries, software and papers

A curated list of speech and natural language processing resources

Finite-state script normalization and processing utilities

A public git version of my research projects, i.e. articles and all that

RE2 is a fast, safe, thread-friendly alternative to backtracking regular expression engines like those used in PCRE, Perl, and Python. It is a C++ library.

Animation engine for explanatory math videos

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

🔍 High-level C++ client for ElasticSearch

Embedded key-value store for read-heavy workloads written in Go

An open source library for deep learning end-to-end dialog systems and chatbots.

XLNet: Generalized Autoregressive Pretraining for Language Understanding

A library for efficient similarity search and clustering of dense vectors.

Ridiculously Simple Strongly Typed API Server with Spring Boot and Swagger

Recurrent neural network grammars

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

Scribe is a server for aggregating log data streamed in real time from a large number of servers.

Blade is a powerful build system from Tencent, supports many mainstream programming languages, such as C/C++, java, scala, python, protobuf...

The missing bridge between Java and native C++

TensorFlow template application for deep learning

The missing bridge between Java and native C++ libraries

The missing Java distribution of native C++ libraries

💥 displaCy.js: An open-source NLP visualiser for the modern web