hotzjacobb

followers

following

stars

Jacob Hotz's starred repositories

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Language:PythonMIT29859 424 4172

fastbook

The fastai book, published as Jupyter Notebooks

Language:Jupyter NotebookNOASSERTION21238 505 235

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Language:PythonMIT19220 297 1339

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

Language:PythonApache-2.014501 134 2066

vision_transformer

Language:Jupyter NotebookApache-2.09803 97 203

boto3

AWS SDK for Python

Language:PythonApache-2.08855 235 3276

bertviz

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

Language:PythonApache-2.06618 71 123

YCSB

Yahoo! Cloud Serving Benchmark

Language:JavaApache-2.04861 215 950

xla

Enabling PyTorch on XLA Devices (e.g. Google TPU)

Language:C++NOASSERTION2386 55 2089

electra

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

Language:PythonApache-2.02315 60 123

bert_score

BERT score for text generation

Language:Jupyter NotebookMIT1514 22 154

word2vec

Automatically exported from code.google.com/p/word2vec

Language:CApache-2.01512 52 45

attention-cnn

Source code for "On the Relationship between Self-Attention and Convolutional Layers"

Language:PythonApache-2.01068 27 10

evojax

Language:Jupyter NotebookApache-2.0816 23 28

pytorch-apple-silicon

Setup PyTorch on Mac/Apple Silicon plus a few benchmarks.

Language:Jupyter NotebookMIT397 11 3

mlm-scoring

Python library & examples for Masked Language Model Scoring (ACL 2020)

Language:PythonApache-2.0333 15 21

BARTScore

BARTScore: Evaluating Generated Text as Text Generation

Language:PythonApache-2.0309 7 44

electra-pytorch

A simple and working implementation of Electra, the fastest way to pretrain language models from scratch, in Pytorch

Language:PythonMIT220 9 11

DiscoBERT

Code for paper "Discourse-Aware Neural Extractive Text Summarization" (ACL20)

Language:PythonMIT165 10 13

commonsenseqa

Author implementation of the paper "CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge"

Language:Python139 3 6

Zero-Shot-DST

Zero-shot dialogue state tracking (DST)

Language:PythonNOASSERTION82 7 3

ACL2020-ConKADI

Resources for the our ACL2020 paper, Diverse and Informative Dialogue Generation with Context-Specific Commonsense Knowledge Awareness

Language:Python40 3 7

CPEN-400Q

Materials for the undergraduate course in gate-model quantum computing at UBC.

MIT37 50

ContraWSD

Word sense disambiguation test sets for NMT

Language:Python19 60

monopoly

Language:Python12 20

wheels_builder

Language:Shell9 27 17

discourse_probing

Discourse Probing of Pretrained Language Models. In Proceedings of NAACL 2021.

Language:Jupyter Notebook9 3 2

NegatER

NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge Bases (EMNLP 2021)

Language:Python6 20

detecting_wsd_biases_for_nmt

Repository containing the experimental code for the publication 'Detecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial Attacks' (Emelin, Denis, Ivan Titov, and Rico Sennrich, EMNLP 2020).

Language:PythonMIT4 20

Pre-Training-is-almost-all-you-Need-for-Commonsense-Reasoning

An (as efficient as possible) implementation of the paper "Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning"

Language:PythonMIT300