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.
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
Fully open reproduction of DeepSeek-R1
Graph Neural Network Library for PyTorch
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.
Machine Learning Engineering Open Book
Pytorch implementation of convolutional neural network visualization techniques
A faster pytorch implementation of faster r-cnn
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
📊 A simple command-line utility for querying and monitoring GPU status
Differentiable architecture search for convolutional and recurrent networks
Modularized Implementation of Deep RL Algorithms in PyTorch
A PyTorch implementation of the YOLO v3 object detection algorithm
A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).
Implementation of Graph Auto-Encoders in TensorFlow
A lightweight library for PyTorch training tools and utilities
A memory-efficient implementation of DenseNets
TensorFlow GNN is a library to build Graph Neural Networks on the TensorFlow platform.
Open Source Generative Process Automation (i.e. Generative RPA). AI-First Process Automation with Large ([Language (LLMs) / Action (LAMs) / Multimodal (LMMs)] / Visual Language (VLMs)) Models
code for EMNLP 2019 paper Text Summarization with Pretrained Encoders
Pytorch implementation of "A simple neural network module for relational reasoning" (Relational Networks)
[ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).
An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.
A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)
Convolutional 2D Knowledge Graph Embeddings resources
[NAACL 2021] QAGNN: Question Answering using Language Models and Knowledge Graphs 🤖
ICLR 2020: Composition-Based Multi-Relational Graph Convolutional Networks
Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging Face 🤗 Transformers.