matt-peters Goto Github PK

allennlp

An open-source NLP research library, built on PyTorch.

allennlp-models

Officially supported AllenNLP models

apex

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

bert

TensorFlow code and pre-trained models for BERT

datasets

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

deep_qa

Using deep learning to answer Aristo's science questions

detectron2

Detectron2 is FAIR's next-generation platform for object detection and segmentation.

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

document-qa

flex

Few-shot NLP benchmark for unified, rigorous eval

jiant

The jiant sentence representation learning toolkit

keras

Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano and TensorFlow.

lm-bff

matt-peters.github.io

moco

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

pytorch-lightning

The lightweight PyTorch wrapper for ML researchers. Scale your models. Write less boilerplate

qdr

Query-Document Relevance

qless

Queue / Pipeline Management

qless-py

Python Bindings for qless

sru

Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

tensorboard_logger

Log TensorBoard events without touching TensorFlow

text

Data loaders and abstractions for text and NLP

text-to-text-transfer-transformer

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

transformers

PyTorch version of Google AI's BERT model with script to load Google's pre-trained models