Stars
Ongoing research training transformer models at scale
data collator for UL2 and U-PaLM
A preliminary evaluation of ChatGPT/GPT-4 for machine translation.
The official Python library for the OpenAI API
Code for visualizing the loss landscape of neural nets
Solve puzzles. Improve your pytorch.
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
A Python framework for sequence labeling evaluation(named-entity recognition, pos tagging, etc...)
Examples for aligning, padding and batching sequence labeling data (NER) for use with pre-trained transformer models
This repository contains the FewGLUE dataset for few-shot natural language understanding.
Multi-Task Deep Neural Networks for Natural Language Understanding
Few-Shot-Intent-Detection includes popular challenging intent detection datasets with/without OOS queries and state-of-the-art baselines and results.
Google Research
Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.
A unified benchmark problem for data poisoning attacks
Modularized Implementation of Deep RL Algorithms in PyTorch
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKT…
Fast, general, and tested differentiable structured prediction in PyTorch
⏰ AI conference deadline countdowns
PyTorch implementation of MAML: https://arxiv.org/abs/1703.03400
Language-Agnostic SEntence Representations
Small utility to monitor fairseq training in tensorboard
Unsupervised text tokenizer for Neural Network-based text generation.
Keras + Hyperopt: A very simple wrapper for convenient hyperparameter optimization