PyTorch native quantization and sparsity for training and inference

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

A Pythonic framework to simplify AI service building

SGLang is yet another fast serving framework for large language models and vision language models.

Tools for curating biomedical training data for large-scale language modeling

Toolkit for collecting and applying templates of prompting instances

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

Code and Data for Evaluation WG

Beyond the Imitation Game collaborative benchmark for enormous language models

A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch

This repository contains my personal notes and summaries on DeepLearning.ai specialization courses. I've enjoyed every little bit of the course hope you enjoy my notes too.

A framework for training and evaluating AI models on a variety of openly available dialog datasets.

Cornell NLVR is a natural language grounding dataset with 92K examples. Each example shows an image and a sentence describing it, and is annotated with the truth-value of the sentence.

Sentence embeddings (InferSent) and training code for NLI.

Tensors and Dynamic neural networks in Python with strong GPU acceleration

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

Computation using data flow graphs for scalable machine learning

Sequence to Sequence Learning with Keras

A living collection of deep learning problems