Thomas Wolf – Medium

Thomas Wolf

Thomas Wolf
in
HuggingFace

🌓 From TensorFlow to PyTorch

Friends and users of our open-source tools are often surprised how fast 🚀 we reimplement the latest SOTA pretrained TensorFlow models to…

7 min readAug 9, 2019

--

2

🌓 From TensorFlow to PyTorch

--

2

Thomas Wolf
in
HuggingFace

🦄 How to build a State-of-the-Art Conversational AI with Transfer-Learning

How you can use Transfer Learning to build a State-of-the-Art chatbot based on OpenAI GPT and GPT-2 Transformer language models

12 min readMay 9, 2019

--

17

🦄 How to build a State-of-the-Art Conversational AI with Transfer-Learning

--

17

Thomas Wolf
in
HuggingFace

💥 Training Neural Nets on Larger Batches: Practical Tips for 1-GPU, Multi-GPU & Distributed setups

Training neural networks with larger batches in PyTorch: gradient accumulation, gradient checkpointing, multi-GPUs and distributed setups…

9 min readOct 15, 2018

--

31

💥 Training Neural Nets on Larger Batches: Practical Tips for 1-GPU, Multi-GPU & Distributed setups

--

31

Thomas Wolf
in
HuggingFace

⛵ Learning Meaning in Natural Language Processing - The Semantics Mega-Thread

In which Twitter talked about meaning, semantics, language models, learning Thai and Java, entailment, co-reference - all in one…

7 min readAug 7, 2018

--

5

⛵ Learning Meaning in Natural Language Processing - The Semantics Mega-Thread

--

5

Thomas Wolf
in
HuggingFace

🚀 100 Times Faster Natural Language Processing in Python

How to take advantage of spaCy & a bit of Cython for blazing fast NLP

10 min readJun 12, 2018

--

12

🚀 100 Times Faster Natural Language Processing in Python

--

12

Thomas Wolf
in
HuggingFace

📚The Current Best of Universal Word Embeddings and Sentence Embeddings

Word & Sentence Embeddings have evolved really fast over the last few months - A brief primer on what happened

9 min readMay 14, 2018

--

21

📚The Current Best of Universal Word Embeddings and Sentence Embeddings

--

21

Thomas Wolf
in
HuggingFace

🐣 From zero to research — An introduction to Meta-learning

Meta-learning is an exciting trend of research in the machine-learning community which tackles the problem of learning to learn.

12 min readApr 3, 2018

--

11

🐣 From zero to research — An introduction to Meta-learning

--

11

Thomas Wolf
in
HuggingFace

✨How to train a neural coreference model— Neuralcoref 2

Links: Online demo Github repo: https://github.com/huggingface/neuralcoref and our previous Medium post.

8 min readMar 23, 2018

--

8

✨How to train a neural coreference model— Neuralcoref 2

--

8

Thomas Wolf
in
HuggingFace

Understanding emotions — from Keras to pyTorch

Introducing torchMoji, a PyTorch implementation of DeepMoji

6 min readOct 4, 2017

--

5

Understanding emotions — from Keras to pyTorch

--

5

Thomas Wolf
in
HuggingFace

State-of-the-art neural coreference resolution for chatbots

TL;DR, Links: Online demo at https://huggingface.co/coref, Github repo for Neuralcoref: https://github.com/huggingface/neuralcoref

9 min readJul 7, 2017

--

10

State-of-the-art neural coreference resolution for chatbots

--

10

Thomas Wolf

Thomas Wolf

Natural Language Processing, Deep learning and Computational Linguistics – Science Lead @Huggingface | thomwolf.io

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams