Highlights
- Pro
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.
Code and documentation to train Stanford's Alpaca models, and generate the data.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv
A library for mechanistic interpretability of GPT-style language models
A Pythonic wrapper for the Wikipedia API
Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)
Benchmark datasets, data loaders, and evaluators for graph machine learning
DeepIE: Deep Learning for Information Extraction
Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch
Open Academic Research on Improving LLaMA to SOTA LLM
TensorFlow implementation of Deep Reinforcement Learning papers
绝区零 | ZenlessZoneZero | 零号空洞 | 自动战斗 | 自动化 | 图片分类 | OCR识别
Code for CRATE (Coding RAte reduction TransformEr).
(Open Source) Computer Vision + Deep Learning + League of Legends
Official Code for Paper: RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text
[ICLR 2020; IPDPS 2019] Fast and accurate minibatch training for deep GNNs and large graphs (GraphSAINT: Graph Sampling Based Inductive Learning Method).
A knowledge base construction engine for richly formatted data
A PyTorch implementation of GraphRel
PyTorch code for "Locating objects without bounding boxes" - Loss function and trained models
Python scripts preprocessing Penn Treebank and Chinese Treebank
Source code of the paper "Do Syntax Trees Help Pre-trained Transformers Extract Information?" (EACL 2021)
Python library to work with ConceptNet offline without the need for PostgreSQL
python implementation of Sobol' sequence generator