Stars
WikiMixQA: A Multimodal Benchmark for Question Answering over Tables and Charts [ACL 2025]
Keymapper config to make Linux keyboard shortcuts work like a 'Tosh! And more. (A Kinto alternative.)
🙃 A delightful community-driven (with 2,400+ contributors) framework for managing your zsh configuration. Includes 300+ optional plugins (rails, git, macOS, hub, docker, homebrew, node, php, python…
Fish-like autosuggestions for zsh
C++ implementation of the Hellinger PCA for computing word embeddings.
BertViz: Visualize Attention in Transformer Models
Open source deep learning based unsupervised image retrieval toolbox built on PyTorch🔥
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
Implements the unsupervised pre-training of convolutional neural networks
Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.
PyTorch implementation of the paper "Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels" in NIPS 2018
FastAPI framework, high performance, easy to learn, fast to code, ready for production
[NeurIPS 2019] Spherical Text Embedding
Streamlit — A faster way to build and share data apps.
Vision-Language Pre-training for Image Captioning and Question Answering
Open source annotation tool for machine learning practitioners.
Multi-Task Deep Neural Networks for Natural Language Understanding
A simple and effective method for detecting out-of-distribution images in neural networks.
Large datasets for conversational AI
pyclustering is a Python, C++ data mining library.
Ekphrasis is a text processing tool, geared towards text from social networks, such as Twitter or Facebook. Ekphrasis performs tokenization, word normalization, word segmentation (for splitting has…
PyTorch original implementation of Cross-lingual Language Model Pretraining.
source code to ICLR'19, 'A Closer Look at Few-shot Classification'
A smaller subset of 10 easily classified classes from Imagenet, and a little more French
🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥
🤗 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.