The AI community building the future. hf.co/careers
NYC and Paris and 🌏
- Tweets 13,814
- Following 222
- Followers 712,857
- Likes 9,169
We just released Transformers' boldest feature: Transformers Agents.
This removes the barrier of entry to machine learning
Control 100,000+ HF models by talking to Transformers and Diffusers
Fully multimodal agent: text, images, video, audio, docs...🌎
huggingface.co/docs/transfor…
ALT A diagram of a HuggingFace behaving like an agent in Matrix
71
780
3,225
617,594
We passed 5 million users.
🥳That's 5 million of you who have signed up on the Hub 🚀 thank you for contributing to the ecosystem and making open Machine Learning happen!
We're just getting started 🤗
253
236
1,959
462,402
Llama 2: Now on Hugging Chat 🤗🦙
Try out the 70B Chat model for free with super fast inference, web search, and powered by open-source tools!
👉 hf.co/chat
34
426
1,692
403,563
THIS IS BIG! 👀
It's now possible to take any of the >30,000 ML apps from Spaces and run them locally (or on your own infrastructure) with the new "Run with @Docker" feature. 🔥🐳
See an app you like? Run it yourself in just 2 clicks🤯
33
327
1,616
240,737
🤗 Transformers has been built by, with, and for the community.
Reaching 100k ⭐ on GitHub is a testament to ML's reach and the community's will to innovate and contribute.
To celebrate, we highlight 100 incredible projects in transformers' vicinity.
github.com/huggingface/trans…
ALT Hugging Faces celebrating the 100k milestone. Highlights that there are many Hugging Faces, as reaching this milestone is really thanks to a huge community building with this tool.
133
277
1,522
477,380
No labeled data? No problem.
The 🤗 Transformers master branch now includes a built-in pipeline for zero-shot text classification, to be included in the next release.
Try it out in the notebook here: colab.research.google.com/dr…
19
407
1,534
The first part of the Hugging Face Course is finally out!
Come learn how the 🤗 Ecosystem works 🥳: Transformers, Tokenizers, Datasets, Accelerate, the Model Hub!
Share with your friends who want to learn NLP, it's free!
Come join us at hf.co/course
23
470
1,468
🚨Transformers is expanding to Speech!🚨
🤗Transformers v4.3.0 is out and we are excited to welcome @facebookai's Wav2Vec2 as the first Automatic Speech Recognition model to our library!
👉Now, you can transcribe your audio files directly on the hub: huggingface.co/facebook/wav2…
ALT Taken from the official Wav2Vec2 paper: https://arxiv.org/abs/2006.11477
17
305
1,355
SAM, the groundbreaking segmentation model from @Meta is now in available in 🤗 Transformers!
What does this mean?
1. One line of code to load it, one line to run it
2. Efficient batching support to generate multiple masks
3. pipeline support for easier usage
More details: 🧵
23
236
1,285
251,333
$40M series B! 🙏Thank you open source contributors, pull requesters, issue openers, notebook creators, model architects, twitting supporters & community members all over the 🌎!
We couldn't do what we do & be where we are - in a field dominated by big tech - without you!
55
134
1,275
Code Llama: Now on Hugging Chat 💻🦙
Try out the 34B Instruct model for free with super fast inference!
👉 hf.co/chat
21
265
1,241
188,872
Last week, EleutherAI released two checkpoints for GPT Neo, an *Open Source* replication of OpenAI's GPT-3
These checkpoints, of sizes 1.3B and 2.7B are now available in🤗Transformers!
The generation capabilities are truly🤯, try it now on the Hub: huggingface.co/EleutherAI/gp…
16
299
1,167
Last week @MetaAI publicly released huge LMs, with up to ☄️30B parameters. Great win for Open-Source🎉
These checkpoints are now in 🤗transformers!
But how to use such big checkpoints?
Introducing Accelerate and
⚡️BIG MODEL INFERENCE⚡️
Load & USE the 30B model in colab (!)⬇️
ALT We load the checkpoint that is saved on disk and we dispatch it to the devices. At no point is the checkpoint fully loaded in RAM; only parts of it to be dispatched to each device. We load it as float16 so that we may load more layers at a time on each device for a faster execution time.
14
231
1,132
The first RNN in transformers! 🤯
Announcing the integration of RWKV models in transformers with @BlinkDL_AI and RWKV community!
RWKV is an attention free model that combines the best from RNNs and transformers.
Learn more about the model in this blogpost: huggingface.co/blog/rwkv
15
254
1,105
277,087
Let’s democratize NLP for all languages! 🌎🌎🌎
Today, with v2.9.1, we are releasing 1,008 machine translation models, covering ` of 140 different languages trained by @jorgtiedemann with @marian, ported by @sam_shleifer. Find your language here: huggingface.co/models?search… [1/4]
19
336
1,084
𝗢𝗨𝗥 𝗗𝗘𝗙𝗜𝗡𝗜𝗧𝗜𝗩𝗘 𝗧𝗨𝗧𝗢𝗥𝗜𝗔𝗟 🔥
How to train a new language model from scratch using Transformers and Tokenizers
➡️ huggingface.co/blog/how-to-t…
13
261
968
Long-range sequence modeling meets 🤗 transformers! We are happy to officially release Reformer, a transformer that can process sequences as long as 500.000 tokens from @GoogleAI. Thanks a million, Nikita Kitaev and @lukaszkaiser! Try it out here: colab.research.google.com/dr…
7
246
959
How to train a Llama 2 chatbot (a step-by-step guide, designed for non-coders)
huggingface.co/blog/Llama2-f…
9
220
947
122,026
We are honored to be awarded the Best Demo Paper for "Transformers: State-of-the-Art Natural Language Processing" at #emnlp2020 😍
Thank you to our wonderful team members and the fantastic community of contributors who make the library possible 🤗🤗🤗
aclweb.org/anthology/2020.em…
ALT Screenshot of "Transformers: State-of-the-Art Natural Language Processing" being announced as the Best Demo Paper at EMNLP
27
132
946
Time to push explainable AI 🔬
exBERT, the visual analysis tool to explore learned representations from @MITIBMLab is now integrated on our model pages for BERT, DistilBERT, RoBERTa, XLM & more! Just click on the tag #exbert on @huggingface’s models page: huggingface.co/models?filter…
5
267
922
日本からの嬉しいお知らせです！rinnaが日本語で学習したJapanese Stable DiffusionがHugging Face Spacesでデモ化されました！ huggingface.co/spaces/rinna/…
2
265
915
🤗 Transformers meets VISION 📸🖼️
v4.6.0 is the first CV dedicated release!
- CLIP @OpenAI, Image-Text similarity or Zero-Shot Image classification
- ViT @GoogleAI, and
- DeiT @facebookai, SOTA Image Classification
Try ViT/DeiT on the hub (Mobile too!):
huggingface.co/google/vit-ba…
9
251
916
🧨Diffusion models have been powering impressive ML apps, enabling DALL-E or Imagen
Introducing 🤗 diffusers: a modular toolbox for diffusion techniques, with a focus on:
🚄Inference pipelines
⏰Schedulers
🏭Models
📃Training examples
github.com/huggingface/diffu…
10
190
892
Introducing PruneBERT, fine-*P*runing BERT's encoder to the size of a high-resolution picture (11MB) while keeping 95% of its original perf!
Based on our latest work on movement pruning: arxiv.org/abs/2005.07683
Code and weights: github.com/huggingface/trans…
huggingface.co/huggingface/p…
15
254
901
Super happy to announce that we are acquiring @pollenrobotics to bring open-source robots to the world! 🤖
Since @RemiCadene joined us from Tesla, we’ve become the most widely used software platform for open robotics thanks to @LeRobotHF and the Hugging Face Hub. Now, we’re taking it a step further by teaming up with Pollen, who is one of the only company in the world that actually ships open-source humanoid robots!
The first robot we’re offering is Reachy 2 — your friendly little lab partner for the AI era that is already in use in labs like Cornell or Carnegie Mellon. It’s a state-of-the-art humanoid robot that is open-source & VR-compatible, built for research, education, and embodied AI experiments. You can already order one for $70,000 by emailing sales@pollen-robotics.com.
We believe robotics could be the next interface for AI — and it should be open, affordable, and hackable. Our vision: a future where everyone from the community can build and control their own robot companions instead of relying on closed, expensive black boxes.
Let’s go open robotics 💪🤖
49
172
905
137,529
Now that neural nets have fast implementations, a bottleneck in pipelines is tokenization: strings➡️model inputs.
Welcome 🤗Tokenizers: ultra-fast & versatile tokenization led by @moi_anthony:
-encode 1GB in 20sec
-BPE/byte-level-BPE/WordPiece/SentencePiece...
-python/js/rust...
11
224
853
We are looking into an incident where a malicious user took control over the Hub organizations of Meta/Facebook & Intel via reused employee passwords that were compromised in a data breach on another site. We will keep you updated 🤗
32
135
784
294,088
Hugging Face is now part of the PyTorch Foundation as a premier member 🤝
We have been collaborating with the PyTorch team for the past four years and are committed to supporting the project.
We share an objective: to lower the barrier of entry to ML.
pytorch.org/blog/hugging-fac…
14
129
780
91,745
Hugging Faceから日本へのお知らせです！
Hugging Faceコースの日本語翻訳を始めました。東北大学のStudent Ambassadorsの皆さんのお陰で第一章の翻訳が終了しました。
今後もコツコツと翻訳していきます。
是非コースを読んでHugging Face Tranformersについて学んで、使ってみてください！
2
218
786
Bored at home? Need a new friend?
Hang out with BART, the newest model available in transformers (thx @sam_shleifer) , with the hefty 2.6 release (notes: github.com/huggingface/trans…). Now you can get state-of-the-art summarization with a few lines of code: 👇👇👇
13
202
722
EleutherAI's GPT-J is now in 🤗 Transformers: a 6 billion, autoregressive model with crazy generative capabilities!
It shows impressive results in:
- 🧮Arithmetics
- ⌨️Code writing
- 👀NLU
- 📜Paper writing
- ...
Play with it to see how powerful it is:
huggingface.co/EleutherAI/gp…
13
168
711
Transformers v2.2 is out, with *4* new models and seq2seq capabilities!
ALBERT is released alongside CamemBERT, implemented by the authors, DistilRoBERTa (twice as fast as RoBERTa-base!) and GPT-2 XL!
Encoder-decoder with ⭐Model2Model⭐
Available on github.com/huggingface/trans…
9
195
697
Today we are excited to announce a new partnership with @awscloud! 🔥
Together, we will accelerate the availability of open-source machine learning 🤝
Read the post 👉 huggingface.co/blog/aws-part…
10
151
691
123,198
Document parsing meets 🤗 Transformers!
📄#LayoutLMv2 and #LayoutXLM by @MSFTResearch are now available! 🔥
They're capable of parsing document images (like PDFs) by incorporating text, layout, and visual information, as in the @gradio demo below ⬇️
huggingface.co/spaces/nielsr…
9
184
672
We are excited to partner with @AIatMeta to welcome Llama 4 Maverick (402B) & Scout (109B) natively multimodal Language Models on the Hugging Face Hub with Xet 🤗
Both MoE models trained on up-to 40 Trillion tokens, pre-trained on 200 languages and significantly outperforms its predecessors Llama 3.1 405B 🔥
Llama 4 Scout would fit on one H100 GPU whilst a Mavericks fits perfectly on a H100 DGX - intelligence truly is too cheap to meter! 💥
24
114
686
49,118
🥁🥁🥁 Welcome to "pytorch-transformers", the 👾 library for Natural Language Processing! github.com/huggingface/pytor…
7
210
672
The 101 for text generation! 💪💪💪
This is an overview of the main decoding methods and how to use them super easily in Transformers with GPT2, XLNet, Bart, T5,...
It includes greedy decoding, beam search, top-k/nucleus sampling,...: huggingface.co/blog/how-to-g… by @PatrickPlaten
11
196
668
Transformers 2.4.0 is out 🤗
- Training transformers from scratch is now supported
- New models, including *FlauBERT*, Dutch BERT, *UmBERTo*
- Revamped documentation
- First multi-modal model, MMBT from @facebookai, text & images
Bye bye Python 2 🙃
github.com/huggingface/trans…
7
160
651
Fine-tuning a *3-billion* parameter model on a single GPU?
Now possible in transformers, thanks to the DeepSpeed/Fairscale integrations!
Thank you @StasBekman for the seamless integration, and thanks to @microsoft and @facebookai teams for their support!
huggingface.co/blog/zero-dee…
8
174
645
You can now visualize Transformers training performance with a seamless @wandb integration. Compare hyperparameters, output metrics, and system stats like GPU utilization across your models!
Step-by-step guide: app.wandb.ai/jxmorris12/hugg…
Colab: colab.research.google.com/dr…
9
174
625
┏━━┓┏━━┓┏━━┓┏━━┓
┗━┓┃┃┏┓┃┗━┓┃┃┏┓┃
┏━┛┃┃┃┃┃┏━┛┃┃┃┃┃
Solving Natural Language Processing!
┃┏━┛┃┃┃┃┃┏━┛┃┃┃┃
┃┗━┓┃┗┛┃┃┗━┓┃┗┛┃
┗━━┛┗━━┛┗━━┛┗━━┛
7
78
632
💃PyTorch-Transformers 1.1.0 is live💃
It includes RoBERTa, the transformer model from @facebookai, current state-of-the-art on the SuperGLUE leaderboard! Thanks to @myleott @julien_c @LysandreJik and all the 100+ contributors!
5
187
625
It's been an exciting year for 🤗Transformers. We tripled the number of weekly active users over 2022, with over 1M users most weeks now and 300k daily pip installs on average🤯
10
82
613
153,060
🚨New release alert 🚨BERT, RoBERTa, GPT2, TransformerXL and most of the community models are now an order of magnitude faster thanks to the integration of the tokenizers library!
Check it out here: github.com/huggingface/trans…
3
138
617
🔥Fine-Tuning @facebookai's Wav2Vec2 for Speech Recognition is now possible in Transformers🔥
Not only for English but for 53 Languages🤯
Check out the tutorials:
👉 Train Wav2Vec2 on TIMIT huggingface.co/blog/fine-tun…
👉 Train XLSR-Wav2Vec2 on Common Voice
huggingface.co/blog/fine-tun…
6
150
610
GPT-3 from @OpenAI got you interested in zero-shot and few-shot learning? You're lucky because our own @joeddav has just released a demo of zero-shot topic classification!
Test how the model can predict a topic it has NEVER been trained on: huggingface.co/zero-shot 🤯🤯🤯
10
173
609
We spend our time finetuning models on tasks like text classif, NER or question answering.
Yet 🤗Transformers had no simple way to let users try these fine-tuned models.
Release 2.3.0 brings Pipelines: thin wrappers around tokenizer + model to ingest/output human-readable data.
4
143
595
Want speedy transformers models w/o a GPU?! 🧐
Starting with transformers v3.1.0 your models can now run at the speed of light on commodity CPUs thanks to ONNX Runtime quantization!🚀. Check out our 2nd blog post with ONNX Runtime on the subject! 🔥
medium.com/microsoftazure/fa…
3
165
610
How big should my language model be? As NLP researchers and practitioners, that question is central. We have built a tool that calculates an optimal model size and training time for your budget so you don't have to. See it in action at huggingface.co/calculator/! [1/2]
8
150
612
The Technology Behind BLOOM Training🌸
Discover how @BigscienceW used @MSFTResearch DeepSpeed + @nvidia Megatron-LM technologies to train the World's Largest Open Multilingual Language Model (BLOOM):
huggingface.co/blog/bloom-me…
8
147
601
We're having some infra issues; we're working on it. Please send hugs! 🤗
In the meantime,
import os
os.environ['HF_HUB_OFFLINE']=1
113
55
590
187,058
GoogleからGemma-2-JPNがリリースされました！このモデルはGemma 2 2Bを日本語でfine-tuneしたものです。Gemma 2の英語での性能と同レベルの性能で日本語をサポートします。
モデル一覧:
huggingface.co/collections/g…
6
169
567
95,512
🔥We're launching the new huggingface.co and it's incredible
🚀Play live with +10 billion parameters models, deploy them instantly in production with our hosted API, join the 500 organizations using our hub to host/share models & datasets
And one more thing... 👇
14
130
574
Release alert: the 🤗datasets library v1.2 is available now!
With:
- 611 datasets you can download in one line of python
- 467 languages covered, 99 with at least 10 datasets
- efficient pre-processing to free you from memory constraints
Try it out at:
github.com/huggingface/datas…
ALT Landing page of the Hugging Face datasets library with 611 datasets in 476 languages
1
149
578
💫 Perceiver IO by @DeepMind is now available in 🤗 Transformers!
A general purpose deep learning model that works on any modality and combinations thereof
📜text
🖼️ images
🎥 video
🔊 audio
☁️ point clouds
...
Read more in our blog post: huggingface.co/blog/perceive…
4
108
585
Hugging Face 🫶 @GoogleColab
With the latest release of huggingface_hub, you don't need to manually log in anymore. Create a secret once and share it with every notebook you run. 🤗
pip install --upgrade huggingface_hub
Check it out!👇
4
105
553
48,072
🖌️ Stable Diffusion meets 🧨Diffusers!
Releasing diffusers==0.2.2 with full support of @StabilityAI's Stable Diffusion & schedulers 🔥
Google colab:
👉 colab.research.google.com/gi…
Code snippet 👇
7
115
564
The ultimate guide to encoder-decoder models!
Today, we're releasing part one explaining how they work and why they have become indispensable for NLG tasks such as summarization and translation.
> colab.research.google.com/dr…
Subscribe for the full series: huggingface.curated.co
4
139
570
Today we're happy to release four new official notebook tutorials available in our documentation and in colab thanks to @MorganFunto to get started with tokenizers and transformer models in just seconds! github.com/huggingface/trans… (1/6)
10
148
541
The 1.5 billion parameter GPT-2 (aka gpt2-xl) is up:
✅ in the transformers repo: github.com/huggingface/trans…
✅ try it out live in Write With Transformer🦄 transformer.huggingface.co/d…
Coming next:
🔘 Detector model based on RoBERTa
Thanks @OpenAI @Miles_Brundage @jackclarkSF and all
10
149
541
This is SO meta 🤓
We trained a generative language model on a dataset of ArXiv NLP papers. You can now get a neural net to write your papers for (with?) you 🔥.
We heard from a few researchers that they're already using it in submitted papers.
transformer.huggingface.co/
12
138
529
Congratulations on the stellar release! 🤩
The model checkpoints and a detailed report - truly Christmas is here!
huggingface.co/collections/d…
4
16
529
46,801
Transformers v4.22 is out, and includes the first VIDEO models! 🎥
💥VideoMAE: masked auto-encoders for video
💥X-CLIP: CLIP for video-language
Other nice goodies:
💥Swin Transformer v2
💥Pegasus-X
💥Donut
💥MobileViT
... and MacOS support (device="mps")!
2
93
526
TRL 🤗 Hugging Face
Excited to announce that we're doubling down on our efforts to democratize RLHF and reinforcement learning with TRL, new addition to the @huggingface family, developed and led by team member @lvwerra 🎉🎉
Train your first RLHF model 👉github.com/huggingface/trl
ALT Two Hugging Faces on the left welcome another Hugging Face on the right. The two on the left are labeled "Transformers" and "Datasets", whereas the Hugging Face on the right is labeled "TRL".
7
118
508
67,776
🔥JAX meets Transformers🔥
@GoogleAI's JAX/Flax library can now be used as Transformers' backbone ML library.
JAX/Flax makes distributed training on TPU effortless and highly efficient!
👉 Google Colab: colab.research.google.com/gi…
👉 Runtime evaluation:
github.com/huggingface/trans…
3
107
511
The new SOTA is in Transformers! DeBERTa-v2 beats the human baseline on SuperGLUE and up to a crazy 91.7% dev accuracy on MNLI task.
Beats T5 while 10x smaller!
DeBERTa-v2 contributed by @Pengcheng2020 from @MSFTResearch
Try it directly on the hub: huggingface.co/microsoft/deb…
5
107
515
1/4. Four NLP tutorials are now available on
@kaggle
! It's now easier than ever to leverage tokenizers and transformer models like BERT, GPT2, RoBERTa, XLNet, DistilBERT,... for your next competition! 💪💪💪! #NLProc #NLP #DataScience #kaggle
3
140
506
📣 Calling all game dev and AI enthusiasts!🎮
Already 400 people signed up for the first Open Source AI Game Jam, where you'll use AI tools to make a game in a weekend🔥
Sign up here 👉 itch.io/jam/open-source-ai-g…
What AI tools? Let's focus today on Audio tools 🔊
⬇️
8
115
496
244,501
We've heard your requests! Over the past few months ... we've been working on a Hugging Face Course!
The release is imminent. Sign-up for the newsletter to know when it comes out: huggingface.curated.co/
Sneak peek; Transfer Learning with @GuggerSylvain:piped.video/watch?v=BqqfQnyj…
9
119
502
GPT-Neo, the #OpenSource cousin of GPT3, can do practically anything in #NLP from sentiment analysis to writing SQL queries: just tell it what to do, in your own words. 🤯
How does it work? 🧐
Want to try it out? 🎮
👉 huggingface.co/blog/few-shot…
8
142
484
Scikit-Learn and 🤗 join forces!
With a growing number of tabular classification & regression checkpoints, we believe statistical ML has its place on the HF Hub.
We're excited to partner with sklearn, statistical ML champion, and move forward together.
blog.scikit-learn.org/update…
ALT Visual showing "Hugging Face and Scikit-Learn join forces"
3
88
483
🔥Transformers' first-ever end-2-end multimodal demo was just released, leveraging LXMERT, SOTA model for visual Q&A!
Model by @HaoTan5, @mohitban47, with an impressive implementation in Transformers by @avalmendoz (@UNCnlp)
Notebook available here: colab.research.google.com/dr… 🤗
5
129
497
Thanks to @srush_nlp, we now have an example of a training module for NER leveraging transformers. Under 300 lines of codes and supports GPUs and TPUs thanks to @PyTorchLightnin!
Colab: colab.research.google.com/dr…
Example: github.com/huggingface/trans…
4
130
490
Transformers v4.13.0 is out and it is *big*:
Vision:
- 🖼️ SegFormer
- 🖨️ ImageGPT
Audio:
- 🔡 Language model support for ASR
Multimodal:
- ⚖️ Vision-Text dual encoders
NLP:
- 🔣 mLUKE
- 🏅 DeBERTa-v3
Trainer:
- 1⃣6⃣ The Trainer now supports BF16/TF32!
🌠New doc frontend 🌠
ALT Showcasing the output of ImageGPT on halves of images
5
87
483
TODAY'S A BIG DAY
Spaces are now publicly available
Build, host, and share your ML apps on @huggingface in just a few minutes.
There's no limit to what you can build. Be creative, and share what you make with the community.
🙏 @streamlit and @gradio
hf.co/spaces/launch
4
135
486
👋 To all JS lovers: NLP is more accessible than ever! You can now leverage the power of DistilBERT-cased for Question Answering w/ just 3 lines of code!!! 🤗
You can even run the model remotely w/ the built-in @TensorFlow Serving compatibility 🚀
github.com/huggingface/node-…
10
123
486
At Hugging Face, we are working to enable you to easily build and serve your own LLMs 🧑💻👨💻👩💻
In this blog, we talk about the amazing world of open-source LLMs, the challenges, and how the Hugging Face ecosystem can help you 🪐
Read about them here 👉huggingface.co/blog/os-llms
7
110
464
74,205
We're thrilled to partner with DeepLearning.AI to create some great new content for their NLP Specialization on Coursera!
With this update, you can access exciting new material and lectures that cover the state of the art in NLP 🧑🏫
coursera.org/specializations…
5
76
464
🥁 We can't wait to share our new inference product with you! 🤩
- it achieves 1ms latency on Transformer models 🏎
- you can deploy it in your own infrastructure ⚡️
- we call it: 🤗 Infinity 🚀
📅 Join us for a live event and demo on 9/28!
app.livestorm.co/hugging-fac…
13
62
475
This might be the biggest AI hackathon ever:
* >6,300 registrants
* Runs for 2 weeks (Nov. 14-30)
* Open to anyone, anywhere virtually
* $20,000 in cash prizes + $3.5M+ in sponsor credits
Hosted by @Anthropic and @Gradio, along with 10 sponsors, join kickoff in 30 minutes 👇
Join us LIVE at MCP's first Birthday kickoff at 10 am PT today!🎂
Don't miss out on details about the celebration from the co-hosts, @Gradio and @AnthropicAI.
🔥 We've also got an exciting lineup of speakers from @Huggingface, @OpenAI, @GoogleDeepMind, @modal, @blaxelAI, @SambaNovaAI, and @nebiustf ready to share their insights.
19
48
478
80,403
Happy to officially include DialoGPT from @MSFTResearch to 🤗transformers (see docs: huggingface.co/transformers/…)
DialoGPT is the first conversational response model added to the library.
Now you can build a state-of-the-art chatbot in just 10 lines of code 👇👇👇
5
116
467
Transformers v3.1.0 is out, first pypi release with 💫 PEGASUS, DPR, mBART 💫
📖 New & simpler docs and tutorials
🎤 Dialogue & zero-shot pipelines
⭐️ New encoder-decoder architectures: Bert2GPT2, Roberta2Roberta, Longformer2Roberta, ...
📕 Named outputs:
7
123
461
Last week, @MetaAI introduced NLLB-200: a massive translation model supporting 200 languages.
Models are now available through the Hugging Face Hub, using 🤗Transformers' main branch.
Models on the Hub: huggingface.co/facebook/nllb…
Learn about NLLB-200: ai.facebook.com/research/no-…
ALT Graphic showing French text entering the NLLB-200 model, and Japanese text going out.
5
137
453
Our Distilbert paper just got accepted at NeurIPS 2019's ECM2 workshop!
- 40% smaller 60% faster than BERT
- 97% of the performance on GLUE
We also distilled GPT2 in an 82M params model💥
All the weights are available in TF2.0 @tensorflow here: github.com/huggingface/trans…
4
95
454
Machine learning demos are increasingly a vital part of releasing a model. Demos allow anyone, not just ML engineers, to try a model, give feedback on predictions, and build trust
That's why we are thrilled to announce @Gradio 3.0: a grounds-up redesign of the Gradio library 🥳
7
91
452
🤗Transformers are starting to work with structured databases!
We just released 🤗Transformers v4.1.1 with TAPAS, a multi-modal model for question answering on tabular data from @googleAI.
Try it out through transformers or our inference API: huggingface.co/google/tapas-…
ALT Using the inference API to ask a query on a table. The model gets it right!
5
90
443
🚨Exciting news! Next week, we’ll be launching a brand-new Audio Course! 🤗
Sign up today (eepurl.com/insvcI) and join us for a LIVE course launch event featuring amazing guests like @DynamicWebPaige, Seokhwan Kim, and @functiontelechy! ⚡️
piped.video/watch?v=wqkKResX…
4
95
436
84,926
Happy to announce we partenered with @onnxai @onnxruntime @microsoft to make state-of-the-art inference up to 5x faster 🚀. NLP for every people and organizations! #msbuild aka.ms/hf-ort-blog1
3
100
436
Our API now includes a brand new pipeline: zero-shot text classification
This feature lets you classify sequences into the specified class names out-of-the-box w/o any additional training in a few lines of code! 🚀
Try it out (and share screenshots 📷): huggingface.co/facebook/bart…
ALT Image of web widget. Text to classify: "I spent a year studying abroad in Paris with my friends during college. We didn't learn much French, but it was the most fun I've ever had." Possible class names: happy, sad, proud, nostalgic, angry Model predicts nostalgic with a score of .678
ALT Image of web widget. Text to classify: "I have a problem with my iphone that needs to be resolved asap!!" Possible class names: urgent, not urgent, phone, tablet, computer Allow multiple true classes? True. Model predicts urgent and phone and does not predict computer, not urgent, or tablet
ALT Image of web widget. Text to classify if a snippet from a news article about a new model developed about Galilean satellites Possible class names: space & cosmos, scientific discovery, microbiology, robots, archeology Model predicts scientific discovery and space & cosmos and does not predict archeology, robots, or microbiology.
ALT Image of web widget. Text to classify is the opening line from Anna Karenina, written in Russian. Possible class names: English, Russian, Arabic, Urdu, Mongolian Model predicts Russian with a score of .775
13
105
433
🤗We are going to invest more in @tensorflow in 2021!
If you want to take part in building the fastest growing NLP open-source library, join us: angel.co/company/hugging-fac…
8
75
415