From 62a253d7a63ac0686ac7ec89d4824920269c35f5 Mon Sep 17 00:00:00 2001 From: Julien Chaumond Date: Fri, 3 Feb 2023 19:14:55 +0100 Subject: [PATCH] New markup: Change format a bit (wrap in HTML comment) (#820) * Change format a bit (wrap in comment) * Update README * update today's blog to new format cc @alaradirik @sayakpaul --- 1b-sentence-embeddings.md | 4 +-- README.md | 17 +++++++--- accelerate-deepspeed.md | 4 +-- accelerate-large-models.md | 4 +-- accelerate-library.md | 4 +-- accelerated-inference.md | 2 +- accelerating-pytorch.md | 4 +-- ai-residency.md | 4 +-- ambassadors.md | 4 +-- annotated-diffusion.md | 4 +-- arxiv.md | 4 +-- asr-chunking.md | 4 +-- audio-datasets.md | 4 +-- autonlp-prodigy.md | 4 +-- autotrain-image-classification.md | 4 +-- bert-101.md | 4 +-- bert-cpu-scaling-part-1.md | 4 +-- bert-cpu-scaling-part-2.md | 4 +-- bert-inferentia-sagemaker.md | 4 +-- big-bird.md | 4 +-- bloom-inference-optimization.md | 4 +-- bloom-inference-pytorch-scripts.md | 4 +-- bloom-megatron-deepspeed.md | 4 +-- bloom.md | 4 +-- carbon-emissions-on-the-hub.md | 4 +-- clipseg-zero-shot.md | 4 +-- codeparrot.md | 4 +-- collaborative-training.md | 4 +-- constrained-beam-search.md | 4 +-- convert-transformers-to-onnx.md | 4 +-- course-launch-event.md | 2 +- cv_state.md | 4 +-- data-measurements-tool.md | 4 +-- datasets-docs-update.md | 4 +-- decision-transformers.md | 4 +-- deep-learning-with-proteins.md | 4 +-- deep-rl-a2c.md | 2 +- deep-rl-dqn.md | 2 +- deep-rl-intro.md | 2 +- deep-rl-pg.md | 2 +- deep-rl-ppo.md | 2 +- deep-rl-q-part1.md | 2 +- deep-rl-q-part2.md | 2 +- ...ace-models-easily-with-amazon-sagemaker.md | 2 +- deploy-tfserving-kubernetes.md | 4 +-- deploy-vertex-ai.md | 4 +-- dialog-agents.md | 4 +-- diffusers-2nd-month.md | 4 +-- diffusers-coreml.md | 4 +-- diffusion-models-event.md | 4 +-- document-ai.md | 4 +-- dreambooth.md | 4 +-- education.md | 4 +-- elixir-bumblebee.md | 4 +-- encoder-decoder.md | 4 +-- ethical-charter-multimodal.md | 4 +-- ethics-soc-1.md | 4 +-- ethics-soc-2.md | 4 +-- eval-on-the-hub.md | 4 +-- evaluating-llm-bias.md | 4 +-- fastai.md | 4 +-- fellowship.md | 4 +-- ...shot-learning-gpt-neo-and-inference-api.md | 4 +-- fine-tune-clip-rsicd.md | 4 +-- fine-tune-segformer.md | 4 +-- fine-tune-vit.md | 4 +-- fine-tune-wav2vec2-english.md | 4 +-- fine-tune-whisper.md | 4 +-- fine-tune-xlsr-wav2vec2.md | 4 +-- getting-started-habana.md | 4 +-- getting-started-with-embeddings.md | 4 +-- gptj-sagemaker.md | 4 +-- gradio-blocks.md | 4 +-- gradio-joins-hf.md | 4 +-- gradio-spaces.md | 4 +-- gradio.md | 4 +-- graphcore-getting-started.md | 2 +- graphcore-update.md | 4 +-- graphcore.md | 4 +-- habana-gaudi-2-benchmark.md | 4 +-- habana.md | 4 +-- hardware-partners-program.md | 4 +-- hf-bitsandbytes-integration.md | 4 +-- how-to-deploy-a-pipeline-to-google-clouds.md | 4 +-- how-to-generate.md | 4 +-- how-to-train-sentence-transformers.md | 4 +-- how-to-train.md | 4 +-- hugging-face-endpoints-on-azure.md | 4 +-- image-search-datasets.md | 4 +-- image-similarity.md | 4 +-- inference-endpoints.md | 4 +-- inference-update.md | 4 +-- infinity-cpu-performance.md | 4 +-- intel-sapphire-rapids.md | 4 +-- intel.md | 4 +-- interns-2023.md | 4 +-- intro-graphml.md | 4 +-- introducing-csearch.md | 4 +-- introducing-doi.md | 4 +-- introducing-private-hub.md | 4 +-- japanese-stable-diffusion.md | 4 +-- large-language-models.md | 4 +-- lewis-tunstall-interview.md | 4 +-- long-range-transformers.md | 4 +-- lora.md | 4 +-- mask2former.md | 4 +-- meg-mitchell-interview.md | 4 +-- megatron-training.md | 4 +-- ml-director-insights-2.md | 4 +-- ml-director-insights-3.md | 4 +-- ml-director-insights-4.md | 2 +- ml-director-insights.md | 4 +-- ml-for-games-1.md | 2 +- ml-for-games-2.md | 2 +- ml-for-games-3.md | 2 +- ml-for-games-4.md | 2 +- mnist-adversarial.md | 4 +-- model-cards.md | 4 +-- mteb.md | 4 +-- nystromformer.md | 4 +-- open_rail.md | 4 +-- openvino.md | 4 +-- opinion-classification-with-kili.md | 4 +-- optimum-inference.md | 4 +-- optimum-onnxruntime-training.md | 4 +-- paddlepaddle.md | 4 +-- perceiver.md | 4 +-- playlist-generator.md | 4 +-- porting-fsmt.md | 4 +-- pretraining-bert.md | 4 +-- pricing-update.md | 4 +-- pytorch-ddp-accelerate-transformers.md | 4 +-- pytorch-fsdp.md | 4 +-- pytorch-xla.md | 4 +-- pytorch_block_sparse.md | 4 +-- ray-rag.md | 4 +-- ray-tune.md | 4 +-- reformer.md | 4 +-- rlhf.md | 4 +-- sagemaker-distributed-training-seq2seq.md | 4 +-- sasha-luccioni-interview.md | 4 +-- sb3.md | 4 +-- searching-the-hub.md | 4 +-- sempre-health-eap-case-study.md | 4 +-- sentence-transformers-in-the-hub.md | 4 +-- sentiment-analysis-fhe.md | 4 +-- sentiment-analysis-python.md | 4 +-- sentiment-analysis-twitter.md | 4 +-- series-c.md | 4 +-- setfit.md | 4 +-- simple-considerations.md | 4 +-- skops.md | 4 +-- snowball-fight.md | 4 +-- spaces_3dmoljs.md | 4 +-- spacy.md | 4 +-- stable_diffusion.md | 4 +-- stable_diffusion_jax.md | 4 +-- streamlit-spaces.md | 4 +-- summer-at-huggingface.md | 4 +-- ...-customer-service-with-machine-learning.md | 4 +-- tapex.md | 4 +-- tensorflow-philosophy.md | 4 +-- tf-serving-vision.md | 4 +-- tf-serving.md | 4 +-- tf-xla-generate.md | 4 +-- the-age-of-ml-as-code.md | 4 +-- time-series-transformers.md | 4 +-- train-decision-transformers.md | 4 +-- transformers-design-philosophy.md | 4 +-- us-national-ai-research-resource.md | 4 +-- vision-transformers.md | 4 +-- vision_language_pretraining.md | 31 ++++--------------- vq-diffusion.md | 4 +-- warm-starting-encoder-decoder.md | 4 +-- wav2vec2-with-ngram.md | 4 +-- your-first-ml-project.md | 4 +-- zero-deepspeed-fairscale.md | 4 +-- zero-shot-eval-on-the-hub.md | 4 +-- 178 files changed, 355 insertions(+), 365 deletions(-) diff --git a/1b-sentence-embeddings.md b/1b-sentence-embeddings.md index ec4c4175ca..5ad7e84fae 100644 --- a/1b-sentence-embeddings.md +++ b/1b-sentence-embeddings.md @@ -7,8 +7,8 @@ authors: # Train a Sentence Embedding Model with 1 Billion Training Pairs -{blog_metadata} -{authors} + + **Sentence embedding** is a method that maps sentences to vectors of real numbers. Ideally, these vectors would capture the semantic of a sentence and be highly generic. Such representations could then be used for many downstream applications such as clustering, text mining, or question answering. diff --git a/README.md b/README.md index de62c40747..ea6da65182 100644 --- a/README.md +++ b/README.md @@ -7,7 +7,7 @@ This is the official repository of the [Hugging Face Blog](https://hf.co/blog). 2️⃣ Create a md (markdown) file, **use a short file name**. For instance, if your title is "Introduction to Deep Reinforcement Learning", the md file name could be `intro-rl.md`. This is important because the **file name will be the blogpost's URL**. -3️⃣ Create a new folder in `assets`. Use the same name as the name of the md file. Optionally you may add a numerical prefix to that folder, using the number that hasn't been used yet. But this is no longer required. i.e. the asset folder in this example will be `123_intro-rl` or `intro-rl`. This folder will contain **your thumbnail only**. The folder number is mostly for (rough) ordering purposes, so it's no big deal if two concurrent articles use the same number. +3️⃣ Create a new folder in `assets`. Use the same name as the name of the md file. Optionally you may add a numerical prefix to that folder, using the number that hasn't been used yet. But this is no longer required. i.e. the asset folder in this example could be `123_intro-rl` or `intro-rl`. This folder will contain **your thumbnail only**. The folder number is mostly for (rough) ordering purposes, so it's no big deal if two concurrent articles use the same number. For the rest of your files, create a mirrored folder in the HuggingFace Documentation Images [repo](https://huggingface.co/datasets/huggingface/documentation-images/tree/main/blog). This is to reduce bloat in the GitHub base repo when cloning and pulling. @@ -29,10 +29,19 @@ authors: # Train your first Decision Transformer -{blog_metadata} -{authors} + + + +Your content here [...] ``` +The blog_metadata and authors HTML comments are meant to mark where in the file will be inserted the following UI elements: +- "Published on [date]" +- "Update on GitHub" button +- avatars of the authors that were listed in authors. + +⚠️ Please keep the blog_metadata and authors comments exactly equal to those strings otherwise they won't be replaced. + 5️⃣ Then, you can add your content. It's markdown system so if you wrote your text on notion just control shift v to copy/paste as markdown. 6️⃣ Modify `_blog.yml` to add your blogpost. @@ -41,7 +50,7 @@ authors: 8️⃣ The article will be **published automatically when you merge your pull request**. -## How to get a responsive thumbnail? +## How to get a nice responsive thumbnail? 1️⃣ Create a `1300x650` image 2️⃣ Use [this template](https://github.com/huggingface/blog/blob/main/assets/thumbnail-template.svg) and fill the content part. diff --git a/accelerate-deepspeed.md b/accelerate-deepspeed.md index 16102ebe87..adb506f305 100644 --- a/accelerate-deepspeed.md +++ b/accelerate-deepspeed.md @@ -8,8 +8,8 @@ authors:

Accelerate Large Model Training using DeepSpeed

-{blog_metadata} -{authors} + + In this post we will look at how we can leverage the **[Accelerate](https://github.com/huggingface/accelerate)** library for training large models which enables users to leverage the ZeRO features of **[DeeSpeed](https://www.deepspeed.ai)**. diff --git a/accelerate-large-models.md b/accelerate-large-models.md index 3ba69c6b48..5785529f2b 100644 --- a/accelerate-large-models.md +++ b/accelerate-large-models.md @@ -7,8 +7,8 @@ authors: # How 🤗 Accelerate runs very large models thanks to PyTorch -{blog_metadata} -{authors} + + ## Load and run large models diff --git a/accelerate-library.md b/accelerate-library.md index e77d2c3e05..d4f642baf0 100644 --- a/accelerate-library.md +++ b/accelerate-library.md @@ -7,8 +7,8 @@ authors: # Introducing 🤗 Accelerate -{blog_metadata} -{authors} + + ## 🤗 Accelerate diff --git a/accelerated-inference.md b/accelerated-inference.md index e7376fc78d..d9af2a7e55 100644 --- a/accelerated-inference.md +++ b/accelerated-inference.md @@ -5,7 +5,7 @@ thumbnail: /blog/assets/09_accelerated_inference/thumbnail.png

How we sped up transformer inference 100x for 🤗 API customers

-{blog_metadata} + 🤗 Transformers has become the default library for data scientists all around the world to explore state of the art NLP models and build new NLP features. With over 5,000 pre-trained and fine-tuned models available, in over 250 languages, it is a rich playground, easily accessible whichever framework you are working in. diff --git a/accelerating-pytorch.md b/accelerating-pytorch.md index 168182e0fe..6953c28a56 100644 --- a/accelerating-pytorch.md +++ b/accelerating-pytorch.md @@ -8,8 +8,8 @@ authors: # Accelerating PyTorch distributed fine-tuning with Intel technologies -{blog_metadata} -{authors} + + For all their amazing performance, state of the art deep learning models often take a long time to train. In order to speed up training jobs, engineering teams rely on distributed training, a divide-and-conquer technique where clustered servers each keep a copy of the model, train it on a subset of the training set, and exchange results to converge to a final model. diff --git a/ai-residency.md b/ai-residency.md index e6e99d09a8..51d3eb193e 100644 --- a/ai-residency.md +++ b/ai-residency.md @@ -7,8 +7,8 @@ authors: # Announcing the 🤗 AI Research Residency Program 🎉 🎉 🎉 -{blog_metadata} -{authors} + + The 🤗 Research Residency Program is a 9-month opportunity to launch or advance your career in machine learning research 🚀. The goal of the residency is to help you grow into an impactful AI researcher. Residents will work alongside Researchers from our Science Team. Together, you will pick a research problem and then develop new machine learning techniques to solve it in an open & collaborative way, with the hope of ultimately publishing your work and making it visible to a wide audience. diff --git a/ambassadors.md b/ambassadors.md index 55dfabd505..d53397a427 100644 --- a/ambassadors.md +++ b/ambassadors.md @@ -7,8 +7,8 @@ authors: # Student Ambassador Program’s call for applications is open! -{blog_metadata} -{authors} + + As an open-source company democratizing machine learning, Hugging Face believes it is essential to **[teach](https://huggingface.co/blog/education)** open-source ML to people from all backgrounds worldwide. **We aim to teach machine learning to 5 million people by 2023**. diff --git a/annotated-diffusion.md b/annotated-diffusion.md index 25c24922df..db72065d72 100644 --- a/annotated-diffusion.md +++ b/annotated-diffusion.md @@ -8,8 +8,8 @@ authors: # The Annotated Diffusion Model -{blog_metadata} -{authors} + + diff --git a/arxiv.md b/arxiv.md index 53932b44cc..c761bbbdc5 100644 --- a/arxiv.md +++ b/arxiv.md @@ -9,8 +9,8 @@ authors: # Hugging Face Machine Learning Demos on arXiv -{blog_metadata} -{authors} + + We’re very excited to announce that Hugging Face has collaborated with arXiv to make papers more accessible, discoverable, and fun! Starting today, [Hugging Face Spaces](https://huggingface.co/spaces) is integrated with arXivLabs through a Demo tab that includes links to demos created by the community or the authors themselves. By going to the Demos tab of your favorite paper, you can find links to open-source demos and try them out immediately 🔥 diff --git a/asr-chunking.md b/asr-chunking.md index 869669fb37..d482ab66c8 100644 --- a/asr-chunking.md +++ b/asr-chunking.md @@ -7,8 +7,8 @@ authors: # Making automatic speech recognition work on large files with Wav2Vec2 in 🤗 Transformers -{blog_metadata} -{authors} + + ``` Tl;dr: This post explains how to use the specificities of the Connectionist diff --git a/audio-datasets.md b/audio-datasets.md index a7c08025a1..0bea43158a 100644 --- a/audio-datasets.md +++ b/audio-datasets.md @@ -7,8 +7,8 @@ authors: # A Complete Guide to Audio Datasets -{blog_metadata} -{authors} + + diff --git a/autonlp-prodigy.md b/autonlp-prodigy.md index d2c2619b82..aa89c55643 100644 --- a/autonlp-prodigy.md +++ b/autonlp-prodigy.md @@ -7,8 +7,8 @@ authors:

Active Learning with AutoNLP and Prodigy

-{blog_metadata} -{authors} + + Active learning in the context of Machine Learning is a process in which you iteratively add labeled data, retrain a model and serve it to the end user. It is an endless process and requires human interaction for labeling/creating the data. In this article, we will discuss how to use [AutoNLP](https://huggingface.co/autonlp) and [Prodigy](https://prodi.gy/) to build an active learning pipeline. diff --git a/autotrain-image-classification.md b/autotrain-image-classification.md index 631dd0d79e..795ce1e811 100644 --- a/autotrain-image-classification.md +++ b/autotrain-image-classification.md @@ -7,8 +7,8 @@ authors: # Image Classification with AutoTrain -{blog_metadata} -{authors} + + diff --git a/bert-101.md b/bert-101.md index b33058d3ac..0eb6858ad7 100644 --- a/bert-101.md +++ b/bert-101.md @@ -7,8 +7,8 @@ authors:

BERT 101 🤗 State Of The Art NLP Model Explained

-{blog_metadata} -{authors} + + diff --git a/bert-cpu-scaling-part-1.md b/bert-cpu-scaling-part-1.md index e1ab8d953b..65bc1058f8 100644 --- a/bert-cpu-scaling-part-1.md +++ b/bert-cpu-scaling-part-1.md @@ -19,8 +19,8 @@ authors: } -{blog_metadata} -{authors} + + # Scaling up BERT-like model Inference on modern CPU - Part 1 diff --git a/bert-cpu-scaling-part-2.md b/bert-cpu-scaling-part-2.md index c7e96f8a9c..01c2de3a57 100644 --- a/bert-cpu-scaling-part-2.md +++ b/bert-cpu-scaling-part-2.md @@ -9,8 +9,8 @@ authors: # Scaling up BERT-like model Inference on modern CPU - Part 2 -{blog_metadata} -{authors} + + diff --git a/bert-inferentia-sagemaker.md b/bert-inferentia-sagemaker.md index e31ca7cd06..1250500b04 100644 --- a/bert-inferentia-sagemaker.md +++ b/bert-inferentia-sagemaker.md @@ -7,8 +7,8 @@ authors:

Accelerate BERT inference with Hugging Face Transformers and AWS Inferentia

-{blog_metadata} -{authors} + + diff --git a/big-bird.md b/big-bird.md index 8a69611dcf..956c53ae31 100644 --- a/big-bird.md +++ b/big-bird.md @@ -7,8 +7,8 @@ authors: # Understanding BigBird's Block Sparse Attention -{blog_metadata} -{authors} + + ## Introduction diff --git a/bloom-inference-optimization.md b/bloom-inference-optimization.md index cf4cbf1884..c4f57c2aff 100644 --- a/bloom-inference-optimization.md +++ b/bloom-inference-optimization.md @@ -6,8 +6,8 @@ authors: ---

Optimization story: Bloom inference

-{blog_metadata} -{authors} + + This article gives you the behind-the-scenes of how we made an efficient inference server that powers bloom. inference server that powers [https://huggingface.co/bigscience/bloom](). diff --git a/bloom-inference-pytorch-scripts.md b/bloom-inference-pytorch-scripts.md index 885207ccd3..e3720257c4 100644 --- a/bloom-inference-pytorch-scripts.md +++ b/bloom-inference-pytorch-scripts.md @@ -8,8 +8,8 @@ authors:

Incredibly Fast BLOOM Inference with DeepSpeed and Accelerate

-{blog_metadata} -{authors} + + This article shows how to get an incredibly fast per token throughput when generating with the 176B parameter [BLOOM model](https://huggingface.co/bigscience/bloom). diff --git a/bloom-megatron-deepspeed.md b/bloom-megatron-deepspeed.md index 711d99c550..94c54ae3c1 100644 --- a/bloom-megatron-deepspeed.md +++ b/bloom-megatron-deepspeed.md @@ -7,8 +7,8 @@ authors:

The Technology Behind BLOOM Training

-{blog_metadata} -{authors} + + diff --git a/bloom.md b/bloom.md index ec7a067b88..6fdd895219 100644 --- a/bloom.md +++ b/bloom.md @@ -18,8 +18,8 @@ authors:

🌸 Introducing The World's Largest Open Multilingual Language Model: BLOOM 🌸

-{blog_metadata} -{authors} + + diff --git a/carbon-emissions-on-the-hub.md b/carbon-emissions-on-the-hub.md index 998ef05f0d..38ecd8a702 100644 --- a/carbon-emissions-on-the-hub.md +++ b/carbon-emissions-on-the-hub.md @@ -9,8 +9,8 @@ authors:

CO2 Emissions and the 🤗 Hub: Leading the Charge

-{blog_metadata} -{authors} + + ## What are CO2 Emissions and why are they important? diff --git a/clipseg-zero-shot.md b/clipseg-zero-shot.md index 0ae16eb212..a6a774883e 100644 --- a/clipseg-zero-shot.md +++ b/clipseg-zero-shot.md @@ -9,8 +9,8 @@ authors: # Zero-shot image segmentation with CLIPSeg -{blog_metadata} -{authors} + + diff --git a/codeparrot.md b/codeparrot.md index ae53230df8..4a1f916a90 100644 --- a/codeparrot.md +++ b/codeparrot.md @@ -7,8 +7,8 @@ authors:

Training CodeParrot 🦜 from Scratch

-{blog_metadata} -{authors} + + In this blog post we'll take a look at what it takes to build the technology behind [GitHub CoPilot](https://copilot.github.com/), an application that provides suggestions to programmers as they code. In this step by step guide, we'll learn how to train a large GPT-2 model called CodeParrot 🦜, entirely from scratch. CodeParrot can auto-complete your Python code - give it a spin [here](https://huggingface.co/spaces/lvwerra/codeparrot-generation). Let's get to building it from scratch! diff --git a/collaborative-training.md b/collaborative-training.md index 22dbfdecea..4bb10f18be 100644 --- a/collaborative-training.md +++ b/collaborative-training.md @@ -9,8 +9,8 @@ authors: # Deep Learning over the Internet: Training Language Models Collaboratively -{blog_metadata} -{authors} + + With the additional help of Quentin Lhoest and Sylvain Lesage. diff --git a/constrained-beam-search.md b/constrained-beam-search.md index df09999c43..1038882226 100644 --- a/constrained-beam-search.md +++ b/constrained-beam-search.md @@ -8,8 +8,8 @@ authors: # Guiding Text Generation with Constrained Beam Search in 🤗 Transformers -{blog_metadata} -{authors} + + Open In Colab diff --git a/convert-transformers-to-onnx.md b/convert-transformers-to-onnx.md index 94b4184dee..3b1212eb2f 100644 --- a/convert-transformers-to-onnx.md +++ b/convert-transformers-to-onnx.md @@ -6,8 +6,8 @@ authors: --- # Convert Transformers to ONNX with Hugging Face Optimum -{blog_metadata} -{authors} + + Hundreds of Transformers experiments and models are uploaded to the [Hugging Face Hub](https://huggingface.co/) every single day. Machine learning engineers and students conducting those experiments use a variety of frameworks like PyTorch, TensorFlow/Keras, or others. These models are already used by thousands of companies and form the foundation of AI-powered products. diff --git a/course-launch-event.md b/course-launch-event.md index cf6eb5c8e4..53e20a3025 100644 --- a/course-launch-event.md +++ b/course-launch-event.md @@ -7,7 +7,7 @@ authors: # Course Launch Community Event -{authors} + We are excited to share that after a lot of work from the Hugging Face team, part 2 of the [Hugging Face Course](https://hf.co/course) will be released on November 15th! Part 1 focused on teaching you how to use a pretrained model, fine-tune it on a text classification task then upload the result to the [Model Hub](https://hf.co/models). Part 2 will focus on all the other common NLP tasks: token classification, language modeling (causal and masked), translation, summarization and question answering. It will also take a deeper dive in the whole Hugging Face ecosystem, in particular [🤗 Datasets](https://github.com/huggingface/datasets) and [🤗 Tokenizers](https://github.com/huggingface/tokenizers). diff --git a/cv_state.md b/cv_state.md index bf83be6579..8914066b28 100644 --- a/cv_state.md +++ b/cv_state.md @@ -7,8 +7,8 @@ authors: # The State of Computer Vision at Hugging Face 🤗 -{blog_metadata} -{authors} + + At Hugging Face, we pride ourselves on democratizing the field of artificial intelligence together with the community. As a part of that mission, we began focusing our efforts on computer vision over the last year. What started as a [PR for having Vision Transformers (ViT) in 🤗 Transformers](https://github.com/huggingface/transformers/pull/10950) has now grown into something much bigger – 8 core vision tasks, over 3000 models, and over 100 datasets on the Hugging Face Hub. diff --git a/data-measurements-tool.md b/data-measurements-tool.md index da9716aa17..02d84edb8a 100644 --- a/data-measurements-tool.md +++ b/data-measurements-tool.md @@ -9,8 +9,8 @@ authors: # Introducing the 🤗 Data Measurements Tool: an Interactive Tool for Looking at Datasets -{blog_metadata} -{authors} + + diff --git a/datasets-docs-update.md b/datasets-docs-update.md index 13e9639b4f..31177cc2fa 100644 --- a/datasets-docs-update.md +++ b/datasets-docs-update.md @@ -7,8 +7,8 @@ authors: # Introducing new audio and vision documentation in 🤗 Datasets -{blog_metadata} -{authors} + + Open and reproducible datasets are essential for advancing good machine learning. At the same time, datasets have grown tremendously in size as rocket fuel for large language models. In 2020, Hugging Face launched 🤗 Datasets, a library dedicated to: diff --git a/decision-transformers.md b/decision-transformers.md index e982efcde8..84bdfd4eb5 100644 --- a/decision-transformers.md +++ b/decision-transformers.md @@ -8,8 +8,8 @@ authors: # Introducing Decision Transformers on Hugging Face 🤗 -{blog_metadata} -{authors} + + At Hugging Face, we are contributing to the ecosystem for Deep Reinforcement Learning researchers and enthusiasts. Recently, we have integrated Deep RL frameworks such as [Stable-Baselines3](https://github.com/DLR-RM/stable-baselines3). diff --git a/deep-learning-with-proteins.md b/deep-learning-with-proteins.md index ae50a6aad5..cdc0271add 100644 --- a/deep-learning-with-proteins.md +++ b/deep-learning-with-proteins.md @@ -7,8 +7,8 @@ authors: # Deep Learning With Proteins -{blog_metadata} -{authors} + + I have two audiences in mind while writing this. One is biologists who are trying to get into machine learning, and the other is machine learners who are trying to get into biology. If you’re not familiar with either biology or machine learning then you’re still welcome to come along, but you might find it a bit confusing at times! And if you’re already familiar with both, then you probably don’t need this post at all - you can just skip straight to our example notebooks to see these models in action: diff --git a/deep-rl-a2c.md b/deep-rl-a2c.md index 169e7e2822..631995522b 100644 --- a/deep-rl-a2c.md +++ b/deep-rl-a2c.md @@ -18,7 +18,7 @@ authors:

Advantage Actor Critic (A2C)

Unit 7, of the Deep Reinforcement Learning Class with Hugging Face 🤗

-{authors} + diff --git a/deep-rl-dqn.md b/deep-rl-dqn.md index f9ebd54b5d..7a66944a19 100644 --- a/deep-rl-dqn.md +++ b/deep-rl-dqn.md @@ -18,7 +18,7 @@ authors:

Deep Q-Learning with Space Invaders

Unit 3, of the Deep Reinforcement Learning Class with Hugging Face 🤗

-{authors} + diff --git a/deep-rl-intro.md b/deep-rl-intro.md index 4954bb0fe0..6456576881 100644 --- a/deep-rl-intro.md +++ b/deep-rl-intro.md @@ -19,7 +19,7 @@ authors:

An Introduction to Deep Reinforcement Learning

Chapter 1 of the Deep Reinforcement Learning Class with Hugging Face 🤗

-{authors} + diff --git a/deep-rl-pg.md b/deep-rl-pg.md index fc24d495f0..6685beb26a 100644 --- a/deep-rl-pg.md +++ b/deep-rl-pg.md @@ -18,7 +18,7 @@ authors:

Policy Gradient with PyTorch

Unit 5, of the Deep Reinforcement Learning Class with Hugging Face 🤗

-{authors} + diff --git a/deep-rl-ppo.md b/deep-rl-ppo.md index 41439cbcd1..4e2ac3f2a9 100644 --- a/deep-rl-ppo.md +++ b/deep-rl-ppo.md @@ -18,7 +18,7 @@ authors:

Proximal Policy Optimization (PPO)

Unit 8, of the Deep Reinforcement Learning Class with Hugging Face 🤗

-{authors} + diff --git a/deep-rl-q-part1.md b/deep-rl-q-part1.md index 8b26bd9bff..271b77a055 100644 --- a/deep-rl-q-part1.md +++ b/deep-rl-q-part1.md @@ -18,7 +18,7 @@ authors:

An Introduction to Q-Learning Part 1

Unit 2, part 1 of the Deep Reinforcement Learning Class with Hugging Face 🤗

-{authors} + diff --git a/deep-rl-q-part2.md b/deep-rl-q-part2.md index b2b05bd2bf..a0b7b5d30e 100644 --- a/deep-rl-q-part2.md +++ b/deep-rl-q-part2.md @@ -18,7 +18,7 @@ authors:

An Introduction to Q-Learning Part 2/2

Unit 2, part 2 of the Deep Reinforcement Learning Class with Hugging Face 🤗

-{authors} + diff --git a/deploy-hugging-face-models-easily-with-amazon-sagemaker.md b/deploy-hugging-face-models-easily-with-amazon-sagemaker.md index 3d69dbcca1..5ccf1b276a 100644 --- a/deploy-hugging-face-models-easily-with-amazon-sagemaker.md +++ b/deploy-hugging-face-models-easily-with-amazon-sagemaker.md @@ -5,7 +5,7 @@ thumbnail: /blog/assets/17_the_partnership_amazon_sagemaker_and_hugging_face/thu hugging-face-and-aws-logo -{blog_metadata} + # **Deploy Hugging Face models easily with Amazon SageMaker 🏎** diff --git a/deploy-tfserving-kubernetes.md b/deploy-tfserving-kubernetes.md index 2a9d794ac9..17533d4d55 100644 --- a/deploy-tfserving-kubernetes.md +++ b/deploy-tfserving-kubernetes.md @@ -10,8 +10,8 @@ authors: # Deploying 🤗 ViT on Kubernetes with TF Serving -{blog_metadata} -{authors} + + # Introduction diff --git a/deploy-vertex-ai.md b/deploy-vertex-ai.md index c57be6f62d..5dc5358c12 100644 --- a/deploy-vertex-ai.md +++ b/deploy-vertex-ai.md @@ -10,8 +10,8 @@ authors: # Deploying 🤗 ViT on Vertex AI -{blog_metadata} -{authors} + + Open In Colab diff --git a/dialog-agents.md b/dialog-agents.md index d17e200f62..af7510ceb9 100644 --- a/dialog-agents.md +++ b/dialog-agents.md @@ -12,8 +12,8 @@ authors: # What Makes a Dialog Agent Useful? ## The techniques behind ChatGPT: RLHF, IFT, CoT, Red teaming, and more -{blog_metadata} -{authors} + + A few weeks ago, ChatGPT emerged and launched the public discourse into a set of obscure acronyms: RLHF, SFT, IFT, CoT, and more, all attributed to the success of ChatGPT. What are these obscure acronyms and why are they so important? We surveyed all the important papers on these topics to categorize these works, summarize takeaways from what has been done, and share what remains to be shown. diff --git a/diffusers-2nd-month.md b/diffusers-2nd-month.md index 57da3e708c..e3701bf177 100644 --- a/diffusers-2nd-month.md +++ b/diffusers-2nd-month.md @@ -7,8 +7,8 @@ authors: # What's new in Diffusers? 🎨 -{blog_metadata} -{authors} + + A month and a half ago we released `diffusers`, a library that provides a modular toolbox for diffusion models across modalities. A couple of weeks later, we released support for Stable Diffusion, a high quality text-to-image model, with a free demo for anyone to try out. Apart from burning lots of GPUs, in the last three weeks the team has decided to add one or two new features to the library that we hope the community enjoys! This blog post gives a high-level overview of the new features in `diffusers` version 0.3! Remember to give a ⭐ to the [GitHub repository](https://github.com/huggingface/diffusers). diff --git a/diffusers-coreml.md b/diffusers-coreml.md index 70a8022bae..058765f07c 100644 --- a/diffusers-coreml.md +++ b/diffusers-coreml.md @@ -7,8 +7,8 @@ authors: # Using Stable Diffusion with Core ML on Apple Silicon -{blog_metadata} -{authors} + + Thanks to Apple engineers, you can now run Stable Diffusion on Apple Silicon using Core ML! diff --git a/diffusion-models-event.md b/diffusion-models-event.md index 144fdf8878..520f246789 100644 --- a/diffusion-models-event.md +++ b/diffusion-models-event.md @@ -8,8 +8,8 @@ authors: # Diffusion Models Live Event -{blog_metadata} -{authors} + + We are excited to share that the [Diffusion Models Class](https://github.com/huggingface/diffusion-models-class) with Hugging Face and Jonathan Whitaker will be **released on November 28th** 🥳! In this free course, you will learn all about the theory and application of diffusion models -- one of the most exciting developments in deep learning this year. If you've never heard of diffusion models, here's a demo to give you a taste of what they can do: diff --git a/document-ai.md b/document-ai.md index 18d140b324..572c0fd97a 100644 --- a/document-ai.md +++ b/document-ai.md @@ -10,8 +10,8 @@ authors: # Accelerating Document AI -{blog_metadata} -{authors} + + Enterprises are full of documents containing knowledge that isn't accessible by digital workflows. These documents can vary from letters, invoices, forms, reports, to receipts. With the improvements in text, vision, and multimodal AI, it's now possible to unlock that information. This post shows you how your teams can use open-source models to build custom solutions for free! diff --git a/dreambooth.md b/dreambooth.md index 24d570ad00..7fe822863c 100644 --- a/dreambooth.md +++ b/dreambooth.md @@ -10,8 +10,8 @@ authors: # Training Stable Diffusion with Dreambooth using 🧨 Diffusers -{blog_metadata} -{authors} + + [Dreambooth](https://dreambooth.github.io/) is a technique to teach new concepts to [Stable Diffusion](https://huggingface.co/blog/stable_diffusion) using a specialized form of fine-tuning. Some people have been using it with a few of their photos to place themselves in fantastic situations, while others are using it to incorporate new styles. [🧨 Diffusers](https://github.com/huggingface/diffusers) provides a Dreambooth [training script](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth). It doesn't take long to train, but it's hard to select the right set of hyperparameters and it's easy to overfit. diff --git a/education.md b/education.md index 44dc81d926..3f1d32fc46 100644 --- a/education.md +++ b/education.md @@ -7,8 +7,8 @@ authors: # Introducing Hugging Face for Education 🤗 -{blog_metadata} -{authors} + + Given that machine learning will make up the overwhelming majority of software development and that non-technical people will be exposed to AI systems more and more, one of the main challenges of AI is adapting and enhancing employee skills. It is also becoming necessary to support teaching staff in proactively taking AI's ethical and critical issues into account. diff --git a/elixir-bumblebee.md b/elixir-bumblebee.md index 14fb1d3c5b..bb39055bcf 100644 --- a/elixir-bumblebee.md +++ b/elixir-bumblebee.md @@ -8,8 +8,8 @@ authors: # From GPT2 to Stable Diffusion: Hugging Face arrives to the Elixir community -{blog_metadata} -{authors} + + The [Elixir](https://elixir-lang.org/) community is glad to announce the arrival of several Neural Networks models, from GPT2 to Stable Diffusion, to Elixir. This is possible thanks to the [just announced Bumblebee library](https://news.livebook.dev/announcing-bumblebee-gpt2-stable-diffusion-and-more-in-elixir-3Op73O), which is an implementation of Hugging Face Transformers in pure Elixir. diff --git a/encoder-decoder.md b/encoder-decoder.md index dfd396dd0e..f45fa7c72b 100644 --- a/encoder-decoder.md +++ b/encoder-decoder.md @@ -7,8 +7,8 @@ authors:

Transformers-based Encoder-Decoder Models

-{blog_metadata} -{authors} + + Open In Colab diff --git a/ethical-charter-multimodal.md b/ethical-charter-multimodal.md index 4cef03c950..2182fe9015 100644 --- a/ethical-charter-multimodal.md +++ b/ethical-charter-multimodal.md @@ -20,8 +20,8 @@ authors: ## Ethical charter - Multimodal project -{blog_metadata} -{authors} + + ## Purpose of the ethical charter diff --git a/ethics-soc-1.md b/ethics-soc-1.md index 77ca40efb3..212653df95 100644 --- a/ethics-soc-1.md +++ b/ethics-soc-1.md @@ -7,8 +7,8 @@ authors: # Ethics and Society Newsletter #1 -{blog_metadata} -{authors} + + Hello, world! diff --git a/ethics-soc-2.md b/ethics-soc-2.md index 2147fc0a1b..72ba1d6cfa 100644 --- a/ethics-soc-2.md +++ b/ethics-soc-2.md @@ -7,8 +7,8 @@ authors: # Machine Learning in development: Let's talk about bias! -{blog_metadata} -{authors} + + _Bias in ML is ubiquitous, and Bias in ML is complex; so complex in fact that no single technical intervention is likely to meaningfully address the problems it engenders. ML models, as sociotechnical systems, amplify social trends that may exacerbate inequities and harmful biases in ways that depend on their deployment context and are constantly evolving._ diff --git a/eval-on-the-hub.md b/eval-on-the-hub.md index 9d2d907df2..c08e4d262b 100644 --- a/eval-on-the-hub.md +++ b/eval-on-the-hub.md @@ -15,8 +15,8 @@ authors: # Announcing Evaluation on the Hub -{blog_metadata} -{authors} + + TL;DR: Today we introduce [Evaluation on the Hub](https://huggingface.co/spaces/autoevaluate/model-evaluator), a new tool powered by [AutoTrain](https://huggingface.co/autotrain) that lets you evaluate any model on any dataset on the Hub without writing a single line of code! diff --git a/evaluating-llm-bias.md b/evaluating-llm-bias.md index 5adb04f490..633d63c1ba 100644 --- a/evaluating-llm-bias.md +++ b/evaluating-llm-bias.md @@ -11,8 +11,8 @@ authors: # Evaluating Language Model Bias with 🤗 Evaluate -{blog_metadata} -{authors} + + While the size and capabilities of large language models have drastically increased over the past couple of years, so too has the concern around biases imprinted into these models and their training data. In fact, many popular language models have been found to be biased against specific [religions](https://www.nature.com/articles/s42256-021-00359-2?proof=t) and [genders](https://aclanthology.org/2021.nuse-1.5.pdf), which can result in the promotion of discriminatory ideas and the perpetuation of harms against marginalized groups. diff --git a/fastai.md b/fastai.md index c07057abd4..fa0552d0e5 100644 --- a/fastai.md +++ b/fastai.md @@ -7,8 +7,8 @@ authors: # Welcome fastai to the Hugging Face Hub -{blog_metadata} -{authors} + + ## Making neural nets uncool again... and sharing them diff --git a/fellowship.md b/fellowship.md index 05f2254f36..ced920ff3f 100644 --- a/fellowship.md +++ b/fellowship.md @@ -8,8 +8,8 @@ authors: # Announcing the Hugging Face Fellowship Program -{blog_metadata} -{authors} + + The Fellowship is a network of exceptional people from different backgrounds who contribute to the Machine Learning open-source ecosystem 🚀. The goal of the program is to empower key contributors to enable them to scale their impact while inspiring others to contribute as well. diff --git a/few-shot-learning-gpt-neo-and-inference-api.md b/few-shot-learning-gpt-neo-and-inference-api.md index c0fb375ded..e11428dfcf 100644 --- a/few-shot-learning-gpt-neo-and-inference-api.md +++ b/few-shot-learning-gpt-neo-and-inference-api.md @@ -7,8 +7,8 @@ authors: # Few-shot learning in practice: GPT-Neo and the 🤗 Accelerated Inference API -{blog_metadata} -{authors} + + In many Machine Learning applications, the amount of available labeled data is a barrier to producing a high-performing model. The latest developments in NLP show that you can overcome this limitation by providing a few examples at inference time with a large language model - a technique known as Few-Shot Learning. In this blog post, we'll explain what Few-Shot Learning is, and explore how a large language model called GPT-Neo, and the 🤗 Accelerated Inference API, can be used to generate your own predictions. diff --git a/fine-tune-clip-rsicd.md b/fine-tune-clip-rsicd.md index 288a38aff5..9063f610a4 100644 --- a/fine-tune-clip-rsicd.md +++ b/fine-tune-clip-rsicd.md @@ -18,8 +18,8 @@ authors: # Fine tuning CLIP with Remote Sensing (Satellite) images and captions -{blog_metadata} -{authors} + + ## Fine tuning CLIP with Remote Sensing (Satellite) images and captions diff --git a/fine-tune-segformer.md b/fine-tune-segformer.md index 8aba31d260..16355728c4 100644 --- a/fine-tune-segformer.md +++ b/fine-tune-segformer.md @@ -9,8 +9,8 @@ authors: # Fine-Tune a Semantic Segmentation Model with a Custom Dataset -{blog_metadata} -{authors} + + diff --git a/fine-tune-vit.md b/fine-tune-vit.md index 320b898470..b292b3fb61 100644 --- a/fine-tune-vit.md +++ b/fine-tune-vit.md @@ -7,8 +7,8 @@ authors: # Fine-Tune ViT for Image Classification with 🤗 Transformers -{blog_metadata} -{authors} + + diff --git a/fine-tune-wav2vec2-english.md b/fine-tune-wav2vec2-english.md index ca0ea7d12b..664d7eb92d 100644 --- a/fine-tune-wav2vec2-english.md +++ b/fine-tune-wav2vec2-english.md @@ -7,8 +7,8 @@ authors: # Fine-Tune Wav2Vec2 for English ASR with 🤗 Transformers -{blog_metadata} -{authors} + + Open In Colab diff --git a/fine-tune-whisper.md b/fine-tune-whisper.md index 3bfc3bed73..d8c7bf417a 100644 --- a/fine-tune-whisper.md +++ b/fine-tune-whisper.md @@ -7,8 +7,8 @@ authors: # Fine-Tune Whisper For Multilingual ASR with 🤗 Transformers -{blog_metadata} -{authors} + + Open In Colab diff --git a/fine-tune-xlsr-wav2vec2.md b/fine-tune-xlsr-wav2vec2.md index cddee8d208..c4ac6ba3a3 100644 --- a/fine-tune-xlsr-wav2vec2.md +++ b/fine-tune-xlsr-wav2vec2.md @@ -7,8 +7,8 @@ authors: # Fine-tuning XLS-R for Multi-Lingual ASR with 🤗 Transformers -{blog_metadata} -{authors} + + Open In Colab diff --git a/getting-started-habana.md b/getting-started-habana.md index 86e1df8ab0..48cc01db4e 100644 --- a/getting-started-habana.md +++ b/getting-started-habana.md @@ -8,8 +8,8 @@ authors: # Getting Started with Transformers on Habana Gaudi -{blog_metadata} -{authors} + + A couple of weeks ago, we've had the pleasure to [announce](https://huggingface.co/blog/habana) that [Habana Labs](https://habana.ai) and [Hugging Face](https://huggingface.co/) would partner to accelerate Transformer model training. diff --git a/getting-started-with-embeddings.md b/getting-started-with-embeddings.md index fa87208f4d..46ecef579b 100644 --- a/getting-started-with-embeddings.md +++ b/getting-started-with-embeddings.md @@ -7,8 +7,8 @@ authors: # Getting Started With Embeddings -{blog_metadata} -{authors} + + Check out this tutorial with the Notebook Companion: diff --git a/gptj-sagemaker.md b/gptj-sagemaker.md index 3ffe1d5b7a..47738fda5d 100644 --- a/gptj-sagemaker.md +++ b/gptj-sagemaker.md @@ -7,8 +7,8 @@ authors:

Deploy GPT-J 6B for inference using Hugging Face Transformers and Amazon SageMaker

-{blog_metadata} -{authors} + + diff --git a/gradio-blocks.md b/gradio-blocks.md index c1ef3ae8ea..0cf99072f0 100644 --- a/gradio-blocks.md +++ b/gradio-blocks.md @@ -7,8 +7,8 @@ authors:

Gradio 3.0 is Out!

-{blog_metadata} -{authors} + + ### Machine Learning Demos diff --git a/gradio-joins-hf.md b/gradio-joins-hf.md index 21856c4205..4da10222ff 100644 --- a/gradio-joins-hf.md +++ b/gradio-joins-hf.md @@ -7,8 +7,8 @@ authors:

Gradio is joining Hugging Face!

-{blog_metadata} -{authors} + +

 

diff --git a/gradio-spaces.md b/gradio-spaces.md index 98b597202b..a94249db80 100644 --- a/gradio-spaces.md +++ b/gradio-spaces.md @@ -7,8 +7,8 @@ authors: # Showcase Your Projects in Spaces using Gradio -{blog_metadata} -{authors} + + It's so easy to demonstrate a Machine Learning project thanks to [Gradio](https://gradio.app/). diff --git a/gradio.md b/gradio.md index 5913e788f0..8d237f86fa 100644 --- a/gradio.md +++ b/gradio.md @@ -9,8 +9,8 @@ authors: > ##### Cross-posted from the [Gradio blog](https://gradio.app/blog/using-huggingface-models). -{blog_metadata} -{authors} + + The **[Hugging Face Model Hub](https://huggingface.co/models)** has more than 10,000 machine learning models submitted by users. You’ll find all kinds of natural language processing models that, for example, translate between Finnish and English or recognize Chinese speech. More recently, the Hub has expanded to even include models for image classification and audio processing. diff --git a/graphcore-getting-started.md b/graphcore-getting-started.md index f2b412b6e3..7f9b520b45 100644 --- a/graphcore-getting-started.md +++ b/graphcore-getting-started.md @@ -10,7 +10,7 @@ authors: # Getting Started with Hugging Face Transformers for IPUs with Optimum -{authors} + Transformer models have proven to be extremely efficient on a wide range of machine learning tasks, such as natural language processing, audio processing, and computer vision. However, the prediction speed of these large models can make them impractical for latency-sensitive use cases like conversational applications or search. Furthermore, optimizing their performance in the real world requires considerable time, effort and skills that are beyond the reach of many companies and organizations. diff --git a/graphcore-update.md b/graphcore-update.md index b16d9fea36..9756eca02a 100644 --- a/graphcore-update.md +++ b/graphcore-update.md @@ -8,8 +8,8 @@ authors: # Graphcore and Hugging Face Launch New Lineup of IPU-Ready Transformers -{blog_metadata} -{authors} + + [Graphcore](https://huggingface.co/hardware/graphcore/) and Hugging Face have significantly expanded the range of Machine Learning modalities and tasks available in [Hugging Face Optimum](https://github.com/huggingface/optimum), an open-source library for Transformers performance optimization. Developers now have convenient access to a wide range of off-the-shelf Hugging Face Transformer models, optimised to deliver the best possible performance on Graphcore’s IPU. diff --git a/graphcore.md b/graphcore.md index 847e0d94b0..91568992d7 100644 --- a/graphcore.md +++ b/graphcore.md @@ -8,8 +8,8 @@ authors: # Hugging Face and Graphcore partner for IPU-optimized Transformers -{blog_metadata} -{authors} + + > ##### Speaking at the 2021 AI Hardware Summit, Hugging Face announced the launch of their new Hardware Partner Program, including device-optimized models and software integrations. Here, Graphcore - creators of the Intelligence Processing Unit (IPU) and a founding member of the program – explain how their partnership with Hugging Face will allow developers to easily accelerate their use of state-of-the-art Transformer models. diff --git a/habana-gaudi-2-benchmark.md b/habana-gaudi-2-benchmark.md index 31b4f18bad..f854fb9f36 100644 --- a/habana-gaudi-2-benchmark.md +++ b/habana-gaudi-2-benchmark.md @@ -7,8 +7,8 @@ authors: # Faster Training and Inference: Habana Gaudi®-2 vs Nvidia A100 80GB -{blog_metadata} -{authors} + + In this article, you will learn how to use [Habana® Gaudi®2](https://habana.ai/training/gaudi2/) to accelerate model training and inference, and train bigger models with 🤗 [Optimum Habana](https://huggingface.co/docs/optimum/habana/index). Then, we present several benchmarks including BERT pre-training, Stable Diffusion inference and T5-3B fine-tuning, to assess the performance differences between first generation Gaudi, Gaudi2 and Nvidia A100 80GB. Spoiler alert - Gaudi2 is about twice faster than Nvidia A100 80GB for both training and inference! diff --git a/habana.md b/habana.md index f26ffe6873..e8c9a88e8e 100644 --- a/habana.md +++ b/habana.md @@ -8,8 +8,8 @@ authors: # Habana Labs and Hugging Face Partner to Accelerate Transformer Model Training -{blog_metadata} -{authors} + + *Santa Clara and San Francisco, CA, April 12th, 2022* diff --git a/hardware-partners-program.md b/hardware-partners-program.md index 3770388ef4..add0e7adda 100644 --- a/hardware-partners-program.md +++ b/hardware-partners-program.md @@ -10,8 +10,8 @@ authors: # Introducing 🤗 Optimum: The Optimization Toolkit for Transformers at Scale -{blog_metadata} -{authors} + + This post is the first step of a journey for Hugging Face to democratize state-of-the-art **Machine Learning production performance**. diff --git a/hf-bitsandbytes-integration.md b/hf-bitsandbytes-integration.md index d3d9b26291..98c27ca611 100644 --- a/hf-bitsandbytes-integration.md +++ b/hf-bitsandbytes-integration.md @@ -9,8 +9,8 @@ authors: # A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using Hugging Face Transformers, Accelerate and bitsandbytes -{blog_metadata} -{authors} + + ![thumbnail](assets/96_hf_bitsandbytes_integration/Thumbnail_blue.png) diff --git a/how-to-deploy-a-pipeline-to-google-clouds.md b/how-to-deploy-a-pipeline-to-google-clouds.md index 4260b9cb96..977081e52f 100644 --- a/how-to-deploy-a-pipeline-to-google-clouds.md +++ b/how-to-deploy-a-pipeline-to-google-clouds.md @@ -8,8 +8,8 @@ authors: # My Journey to a serverless transformers pipeline on
Google Cloud -{blog_metadata} -{authors} + + > ##### A guest blog post by community member Maxence Dominici diff --git a/how-to-generate.md b/how-to-generate.md index 3622173d38..6e63408651 100644 --- a/how-to-generate.md +++ b/how-to-generate.md @@ -7,8 +7,8 @@ authors:

How to generate text: using different decoding methods for language generation with Transformers

-{blog_metadata} -{authors} + + Open In Colab diff --git a/how-to-train-sentence-transformers.md b/how-to-train-sentence-transformers.md index 3dc2780acd..751b371daa 100644 --- a/how-to-train-sentence-transformers.md +++ b/how-to-train-sentence-transformers.md @@ -7,8 +7,8 @@ authors: # Train and Fine-Tune Sentence Transformers Models -{blog_metadata} -{authors} + + Check out this tutorial with the Notebook Companion: diff --git a/how-to-train.md b/how-to-train.md index b70a5cdf40..456115aef8 100644 --- a/how-to-train.md +++ b/how-to-train.md @@ -7,8 +7,8 @@ authors:

How to train a new language model from scratch using Transformers and Tokenizers

-{blog_metadata} -{authors} + + Open In Colab diff --git a/hugging-face-endpoints-on-azure.md b/hugging-face-endpoints-on-azure.md index 2058e395d1..4a2f781669 100644 --- a/hugging-face-endpoints-on-azure.md +++ b/hugging-face-endpoints-on-azure.md @@ -8,8 +8,8 @@ authors: # Hugging Face Collaborates with Microsoft to Launch Hugging Face Endpoints on Azure -{blog_metadata} -{authors} + + ![Hugging Face Endpoints on Azure](assets/75_hugging_face_endpoints_on_azure/01.png "Hugging Face Endpoints on Azure") diff --git a/image-search-datasets.md b/image-search-datasets.md index 40eaf94f83..13c7009466 100644 --- a/image-search-datasets.md +++ b/image-search-datasets.md @@ -8,8 +8,8 @@ authors:

Image search with 🤗 datasets

-{blog_metadata} -{authors} + + Open In Colab diff --git a/image-similarity.md b/image-similarity.md index 58f8f959aa..e1a440b74f 100644 --- a/image-similarity.md +++ b/image-similarity.md @@ -7,8 +7,8 @@ authors: # Image Similarity with Hugging Face Datasets and Transformers -{blog_metadata} -{authors} + + Open In Colab diff --git a/inference-endpoints.md b/inference-endpoints.md index 553b4db9c9..8771cff81b 100644 --- a/inference-endpoints.md +++ b/inference-endpoints.md @@ -7,8 +7,8 @@ authors: # Getting Started with Hugging Face Inference Endpoints -{blog_metadata} -{authors} + + Training machine learning models has become quite simple, especially with the rise of pre-trained models and transfer learning. OK, sometimes it's not *that* simple, but at least, training models will never break critical applications, and make customers unhappy about your quality of service. Deploying models, however... Yes, we've all been there. diff --git a/inference-update.md b/inference-update.md index 38882ee5d2..ad63ed447d 100644 --- a/inference-update.md +++ b/inference-update.md @@ -7,8 +7,8 @@ authors:

An Overview of Inference Solutions on Hugging Face

-{blog_metadata} -{authors} + + Every day, developers and organizations are adopting models hosted on [Hugging Face](https://huggingface.co/models) to turn ideas into proof-of-concept demos, and demos into production-grade applications. For instance, Transformer models have become a popular architecture for a wide range of machine learning (ML) applications, including natural language processing, computer vision, speech, and more. Recently, diffusers have become a popular architecuture for text-to-image or image-to-image generation. Other architectures are popular for other tasks, and we host all of them on the HF Hub! diff --git a/infinity-cpu-performance.md b/infinity-cpu-performance.md index e917ae849e..7aa1e6ba33 100644 --- a/infinity-cpu-performance.md +++ b/infinity-cpu-performance.md @@ -8,8 +8,8 @@ authors: ---

Case Study: Millisecond Latency using Hugging Face Infinity and modern CPUs

-{blog_metadata} -{authors} + + diff --git a/intel-sapphire-rapids.md b/intel-sapphire-rapids.md index fce4320488..5a9724b7d4 100644 --- a/intel-sapphire-rapids.md +++ b/intel-sapphire-rapids.md @@ -9,8 +9,8 @@ authors: Accelerating PyTorch Transformers with Intel Sapphire Rapids, part 1 -{blog_metadata} -{authors} + + About a year ago, we [showed you](https://huggingface.co/blog/accelerating-pytorch) how to distribute the training of Hugging Face transformers on a cluster or third-generation [Intel Xeon Scalable](https://www.intel.com/content/www/us/en/products/details/processors/xeon/scalable.html) CPUs (aka Ice Lake). Recently, Intel has launched the fourth generation of Xeon CPUs, code-named Sapphire Rapids, with exciting new instructions that speed up operations commonly found in deep learning models. diff --git a/intel.md b/intel.md index f9e2094612..b798a7261f 100644 --- a/intel.md +++ b/intel.md @@ -11,8 +11,8 @@ authors: -{blog_metadata} -{authors} + + ![image](assets/80_intel/01.png) diff --git a/interns-2023.md b/interns-2023.md index 8895ead142..094f3d00d3 100644 --- a/interns-2023.md +++ b/interns-2023.md @@ -8,8 +8,8 @@ authors: # We are hiring interns! -{blog_metadata} -{authors} + + Want to help build the future at -- if we may say so ourselves -- one of the coolest places in AI? Today we’re announcing our internship program for 2023. Together with your Hugging Face mentor(s), we’ll be working on cutting edge problems in AI and machine learning. diff --git a/intro-graphml.md b/intro-graphml.md index c7eabe829b..0c98a4bb1b 100644 --- a/intro-graphml.md +++ b/intro-graphml.md @@ -7,8 +7,8 @@ authors: # Introduction to Graph Machine Learning -{blog_metadata} -{authors} + + In this blog post, we cover the basics of graph machine learning. diff --git a/introducing-csearch.md b/introducing-csearch.md index 452c6f7128..c78f99db9f 100644 --- a/introducing-csearch.md +++ b/introducing-csearch.md @@ -7,8 +7,8 @@ authors:

Generating Human-level Text with Contrastive Search in Transformers 🤗

-{blog_metadata} -{authors} + + **** diff --git a/introducing-doi.md b/introducing-doi.md index 2495f3d765..fdc26ad7d0 100644 --- a/introducing-doi.md +++ b/introducing-doi.md @@ -14,8 +14,8 @@ authors: # Introducing DOI: the Digital Object Identifier to Datasets and Models -{blog_metadata} -{authors} + + Our mission at Hugging Face is to democratize good machine learning. That includes best practices that make ML models and datasets more reproducible, better documented, and easier to use and share. diff --git a/introducing-private-hub.md b/introducing-private-hub.md index 21e6bdc038..1c3a8427d9 100644 --- a/introducing-private-hub.md +++ b/introducing-private-hub.md @@ -7,8 +7,8 @@ authors:

Introducing the Private Hub: A New Way to Build With Machine Learning

-{blog_metadata} -{authors} + + diff --git a/japanese-stable-diffusion.md b/japanese-stable-diffusion.md index 9548bad6bc..ce0465c81a 100644 --- a/japanese-stable-diffusion.md +++ b/japanese-stable-diffusion.md @@ -10,8 +10,8 @@ authors: # Japanese Stable Diffusion -{blog_metadata} -{authors} + + Open In Hugging Face Spaces diff --git a/large-language-models.md b/large-language-models.md index 8c0607aa09..e07da8c200 100644 --- a/large-language-models.md +++ b/large-language-models.md @@ -8,8 +8,8 @@ authors: # Large Language Models: A New Moore's Law? -{blog_metadata} -{authors} + + A few days ago, Microsoft and NVIDIA [introduced](https://www.microsoft.com/en-us/research/blog/using-deepspeed-and-megatron-to-train-megatron-turing-nlg-530b-the-worlds-largest-and-most-powerful-generative-language-model/) Megatron-Turing NLG 530B, a Transformer-based model hailed as "*the world’s largest and most powerful generative language model*." diff --git a/lewis-tunstall-interview.md b/lewis-tunstall-interview.md index f49b564841..5b785ef584 100644 --- a/lewis-tunstall-interview.md +++ b/lewis-tunstall-interview.md @@ -7,8 +7,8 @@ authors:

Machine Learning Experts - Lewis Tunstall

-{blog_metadata} -{authors} + + ## 🤗 Welcome to Machine Learning Experts - Lewis Tunstall diff --git a/long-range-transformers.md b/long-range-transformers.md index 95db42b67f..6259d66574 100644 --- a/long-range-transformers.md +++ b/long-range-transformers.md @@ -12,8 +12,8 @@ authors: # Hugging Face Reads, Feb. 2021 - Long-range Transformers -{blog_metadata} -{authors} + + Co-written by Teven Le Scao, Patrick Von Platen, Suraj Patil, Yacine Jernite and Victor Sanh. diff --git a/lora.md b/lora.md index 8b5d089d01..0e4b22c060 100644 --- a/lora.md +++ b/lora.md @@ -8,8 +8,8 @@ authors: # Using LoRA for Efficient Stable Diffusion Fine-Tuning -{blog_metadata} -{authors} + + [LoRA: Low-Rank Adaptation of Large Language Models](https://arxiv.org/abs/2106.09685) is a novel technique introduced by Microsoft researchers to deal with the problem of fine-tuning large-language models. Powerful models with billions of parameters, such as GPT-3, are prohibitively expensive to fine-tune in order to adapt them to particular tasks or domains. LoRA proposes to freeze pre-trained model weights and inject trainable layers (_rank-decomposition matrices_) in each transformer block. This greatly reduces the number of trainable parameters and GPU memory requirements since gradients don't need to be computed for most model weights. The researchers found that by focusing on the Transformer attention blocks of large-language models, fine-tuning quality with LoRA was on par with full model fine-tuning while being much faster and requiring less compute. diff --git a/mask2former.md b/mask2former.md index 0304b2292f..ca8e93224a 100644 --- a/mask2former.md +++ b/mask2former.md @@ -9,8 +9,8 @@ authors: # Universal Image Segmentation with Mask2Former and OneFormer -{blog_metadata} -{authors} + + diff --git a/meg-mitchell-interview.md b/meg-mitchell-interview.md index 61086cf558..710a7a9422 100644 --- a/meg-mitchell-interview.md +++ b/meg-mitchell-interview.md @@ -7,8 +7,8 @@ authors:

Machine Learning Experts - Margaret Mitchell

-{blog_metadata} -{authors} + + Hey friends! Welcome to Machine Learning Experts. I'm your host, Britney Muller and today’s guest is none other than [Margaret Mitchell](https://twitter.com/mmitchell_ai) (Meg for short). Meg founded & co-led Google’s Ethical AI Group, is a pioneer in the field of Machine Learning, has published over 50 papers, and is a leading researcher in Ethical AI. diff --git a/megatron-training.md b/megatron-training.md index abad8a6b3f..c8fd0774c9 100644 --- a/megatron-training.md +++ b/megatron-training.md @@ -7,8 +7,8 @@ authors:

How to train a Language Model with Megatron-LM

-{blog_metadata} -{authors} + + Training large language models in Pytorch requires more than a simple training loop. It is usually distributed across multiple devices, with many optimization techniques for a stable and efficient training. Hugging Face 🤗 [Accelerate](https://huggingface.co/docs/accelerate/index) library was created to support distributed training across GPUs and TPUs with very easy integration into the training loops. 🤗 [Transformers](https://huggingface.co/docs/transformers/index) also support distributed training through the [Trainer](https://huggingface.co/docs/transformers/main_classes/trainer#transformers.Trainer) API, which provides feature-complete training in PyTorch, without even needing to implement a training loop. diff --git a/ml-director-insights-2.md b/ml-director-insights-2.md index afa8ac35c2..cb9555fe96 100644 --- a/ml-director-insights-2.md +++ b/ml-director-insights-2.md @@ -14,8 +14,8 @@ authors:

Director of Machine Learning Insights [Part 2: SaaS Edition]

-{blog_metadata} -{authors} + + diff --git a/ml-director-insights-3.md b/ml-director-insights-3.md index 00de4bcc18..c030fd8a0e 100644 --- a/ml-director-insights-3.md +++ b/ml-director-insights-3.md @@ -14,8 +14,8 @@ authors:

Director of Machine Learning Insights [Part 3: Finance Edition]

-{blog_metadata} -{authors} + + diff --git a/ml-director-insights-4.md b/ml-director-insights-4.md index c2adc50df9..55dd55e0ee 100644 --- a/ml-director-insights-4.md +++ b/ml-director-insights-4.md @@ -12,7 +12,7 @@ thumbnail: /blog/assets/78_ml_director_insights/part4.png

Director of Machine Learning Insights [Part 4]

-{blog_metadata} + diff --git a/ml-director-insights.md b/ml-director-insights.md index 194fca76a0..a55acbf2f9 100644 --- a/ml-director-insights.md +++ b/ml-director-insights.md @@ -14,8 +14,8 @@ authors:

Director of Machine Learning Insights [Part 1]

-{blog_metadata} -{authors} + + diff --git a/ml-for-games-1.md b/ml-for-games-1.md index 8722d02072..81752c8ffe 100644 --- a/ml-for-games-1.md +++ b/ml-for-games-1.md @@ -7,7 +7,7 @@ authors:

AI for Game Development: Creating a Farming Game in 5 Days. Part 1

-{authors} + diff --git a/ml-for-games-2.md b/ml-for-games-2.md index 37264a77bd..47f5632750 100644 --- a/ml-for-games-2.md +++ b/ml-for-games-2.md @@ -7,7 +7,7 @@ authors:

AI for Game Development: Creating a Farming Game in 5 Days. Part 2

-{authors} + diff --git a/ml-for-games-3.md b/ml-for-games-3.md index da2890b01c..c40439fc6b 100644 --- a/ml-for-games-3.md +++ b/ml-for-games-3.md @@ -7,7 +7,7 @@ authors:

3D Asset Generation: AI for Game Development #3

-{authors} + diff --git a/ml-for-games-4.md b/ml-for-games-4.md index 4f2088a036..0eb0a44140 100644 --- a/ml-for-games-4.md +++ b/ml-for-games-4.md @@ -7,7 +7,7 @@ authors:

2D Asset Generation: AI for Game Development #4

-{authors} + diff --git a/mnist-adversarial.md b/mnist-adversarial.md index 5e7be7c447..cb82698d2e 100644 --- a/mnist-adversarial.md +++ b/mnist-adversarial.md @@ -7,8 +7,8 @@ authors: # How to train your model dynamically using adversarial data -{blog_metadata} -{authors} + + ##### What you will learn here - 💡the basic idea of dynamic adversarial data collection and why it is important. diff --git a/model-cards.md b/model-cards.md index a6326a0b38..ed71036c2b 100644 --- a/model-cards.md +++ b/model-cards.md @@ -9,8 +9,8 @@ authors: # Model Cards -{blog_metadata} -{authors} + + ## Introduction Model cards are an important documentation framework for understanding, sharing, and improving machine learning models. When done well, a model card can serve as a _boundary object_, a single artefact that is accessible to people with different backgrounds and goals in understanding models - including developers, students, policymakers, ethicists, and those impacted by machine learning models. diff --git a/mteb.md b/mteb.md index 5c47406fa2..870fe66c22 100644 --- a/mteb.md +++ b/mteb.md @@ -8,8 +8,8 @@ authors:

MTEB: Massive Text Embedding Benchmark

-{blog_metadata} -{authors} + + MTEB is a massive benchmark for measuring the performance of text embedding models on diverse embedding tasks. diff --git a/nystromformer.md b/nystromformer.md index 556189e8fe..04f092a438 100644 --- a/nystromformer.md +++ b/nystromformer.md @@ -8,8 +8,8 @@ authors:

Nyströmformer: Approximating self-attention in linear time and memory via the Nyström method

-{blog_metadata} -{authors} + + diff --git a/open_rail.md b/open_rail.md index a592fc184e..eb29775aee 100644 --- a/open_rail.md +++ b/open_rail.md @@ -8,8 +8,8 @@ authors:

OpenRAIL: Towards open and responsible AI licensing frameworks

-{blog_metadata} -{authors} + + Open & Responsible AI licenses ("OpenRAIL") are AI-specific licenses enabling open access, use and distribution of AI artifacts while requiring a responsible use of the latter. OpenRAIL licenses could be for open and responsible ML what current open software licenses are to code and Creative Commons to general content: **a widespread community licensing tool.** diff --git a/openvino.md b/openvino.md index f061e72366..2625349fb2 100644 --- a/openvino.md +++ b/openvino.md @@ -8,8 +8,8 @@ authors:

Accelerate your models with 🤗 Optimum Intel and OpenVINO

-{blog_metadata} -{authors} + + ![image](assets/113_openvino/thumbnail.png) diff --git a/opinion-classification-with-kili.md b/opinion-classification-with-kili.md index 39b35100c1..8af7cde492 100644 --- a/opinion-classification-with-kili.md +++ b/opinion-classification-with-kili.md @@ -8,8 +8,8 @@ authors: # Opinion Classification with Kili and HuggingFace AutoTrain -{blog_metadata} -{authors} + + ## Introduction diff --git a/optimum-inference.md b/optimum-inference.md index d2a3fd97ea..2ed8e88905 100644 --- a/optimum-inference.md +++ b/optimum-inference.md @@ -7,8 +7,8 @@ authors: # Accelerated Inference with Optimum and Transformers Pipelines -{blog_metadata} -{authors} + + > Inference has landed in Optimum with support for Hugging Face Transformers pipelines, including text-generation using ONNX Runtime. diff --git a/optimum-onnxruntime-training.md b/optimum-onnxruntime-training.md index 75ee4ebade..902e64fbcd 100644 --- a/optimum-onnxruntime-training.md +++ b/optimum-onnxruntime-training.md @@ -15,8 +15,8 @@ authors: # Optimum + ONNX Runtime: Easier, Faster training for your Hugging Face models -{blog_metadata} -{authors} + + ## Introduction diff --git a/paddlepaddle.md b/paddlepaddle.md index 13fa112969..2b772f3476 100644 --- a/paddlepaddle.md +++ b/paddlepaddle.md @@ -8,8 +8,8 @@ authors: # Welcome PaddlePaddle to the Hugging Face Hub -{blog_metadata} -{authors} + + We are happy to share an open source collaboration between Hugging Face and [PaddlePaddle](https://www.paddlepaddle.org.cn/en) on a shared mission to advance and democratize AI through open source! diff --git a/perceiver.md b/perceiver.md index cecece3761..0a73d68c1e 100644 --- a/perceiver.md +++ b/perceiver.md @@ -7,8 +7,8 @@ authors:

Perceiver IO: a scalable, fully-attentional model that works on any modality

-{blog_metadata} -{authors} + + ### TLDR diff --git a/playlist-generator.md b/playlist-generator.md index 43a22bcdca..8761ea277f 100644 --- a/playlist-generator.md +++ b/playlist-generator.md @@ -7,8 +7,8 @@ authors: # Building a Playlist Generator with Sentence Transformers -{blog_metadata} -{authors} + + diff --git a/porting-fsmt.md b/porting-fsmt.md index 13bdf83994..0378df5ee5 100644 --- a/porting-fsmt.md +++ b/porting-fsmt.md @@ -8,8 +8,8 @@ authors:

Porting fairseq wmt19 translation system to transformers

-{blog_metadata} -{authors} + + ##### A guest blog post by Stas Bekman diff --git a/pretraining-bert.md b/pretraining-bert.md index 677a28661c..2efdcf752e 100644 --- a/pretraining-bert.md +++ b/pretraining-bert.md @@ -7,8 +7,8 @@ authors: # Pre-Training BERT with Hugging Face Transformers and Habana Gaudi -{blog_metadata} -{authors} + + In this Tutorial, you will learn how to pre-train [BERT-base](https://huggingface.co/bert-base-uncased) from scratch using a Habana Gaudi-based [DL1 instance](https://aws.amazon.com/ec2/instance-types/dl1/) on AWS to take advantage of the cost-performance benefits of Gaudi. We will use the Hugging Face [Transformers](https://huggingface.co/docs/transformers), [Optimum Habana](https://huggingface.co/docs/optimum/habana/index) and [Datasets](https://huggingface.co/docs/datasets) libraries to pre-train a BERT-base model using masked-language modeling, one of the two original BERT pre-training tasks. Before we get started, we need to set up the deep learning environment. diff --git a/pricing-update.md b/pricing-update.md index a9919641ea..c8b67203cd 100644 --- a/pricing-update.md +++ b/pricing-update.md @@ -8,8 +8,8 @@ authors:

Introducing our new pricing

-{blog_metadata} -{authors} + + As you might have noticed, our [pricing page](https://huggingface.co/pricing) has changed a lot recently. diff --git a/pytorch-ddp-accelerate-transformers.md b/pytorch-ddp-accelerate-transformers.md index 5bc1f6d3d0..07ac39f725 100644 --- a/pytorch-ddp-accelerate-transformers.md +++ b/pytorch-ddp-accelerate-transformers.md @@ -7,8 +7,8 @@ authors: # From PyTorch DDP to Accelerate to Trainer, mastery of distributed training with ease -{blog_metadata} -{authors} + + ## General Overview diff --git a/pytorch-fsdp.md b/pytorch-fsdp.md index 3662931fb7..870c43a162 100644 --- a/pytorch-fsdp.md +++ b/pytorch-fsdp.md @@ -8,8 +8,8 @@ authors:

Accelerate Large Model Training using PyTorch Fully Sharded Data Parallel

-{blog_metadata} -{authors} + + In this post we will look at how we can leverage **[Accelerate](https://github.com/huggingface/accelerate)** Library for training large models which enables users to leverage the latest features of **[PyTorch FullyShardedDataParallel (FSDP)](https://pytorch.org/blog/introducing-pytorch-fully-sharded-data-parallel-api/)**. diff --git a/pytorch-xla.md b/pytorch-xla.md index 4a3067b944..da1311fcd3 100644 --- a/pytorch-xla.md +++ b/pytorch-xla.md @@ -9,8 +9,8 @@ authors:

Hugging Face on PyTorch / XLA TPUs: Faster and cheaper training

-{blog_metadata} -{authors} + + Open In Colab diff --git a/pytorch_block_sparse.md b/pytorch_block_sparse.md index 56e7148fba..02a654baed 100644 --- a/pytorch_block_sparse.md +++ b/pytorch_block_sparse.md @@ -7,8 +7,8 @@ authors:

Block Sparse Matrices for Smaller and Faster Language Models

-{blog_metadata} -{authors} + + ## Saving space and time, one zero at a time diff --git a/ray-rag.md b/ray-rag.md index 5e4a86c7a4..adc878b91e 100644 --- a/ray-rag.md +++ b/ray-rag.md @@ -8,8 +8,8 @@ authors: # Retrieval Augmented Generation with Huggingface Transformers and Ray -{blog_metadata} -{authors} + + ##### A guest blog post by Amog Kamsetty from the Anyscale team diff --git a/ray-tune.md b/ray-tune.md index 2b175fd994..338bcc67e6 100644 --- a/ray-tune.md +++ b/ray-tune.md @@ -8,8 +8,8 @@ authors: # Hyperparameter Search with Transformers and Ray Tune -{blog_metadata} -{authors} + + ##### A guest blog post by Richard Liaw from the Anyscale team diff --git a/reformer.md b/reformer.md index abede30e9a..00e5cd2a7d 100644 --- a/reformer.md +++ b/reformer.md @@ -7,8 +7,8 @@ authors:

The Reformer - Pushing the limits of language modeling

-{blog_metadata} -{authors} + + Open In Colab diff --git a/rlhf.md b/rlhf.md index b14e8a342a..262805a99f 100644 --- a/rlhf.md +++ b/rlhf.md @@ -10,8 +10,8 @@ authors: # Illustrating Reinforcement Learning from Human Feedback (RLHF) -{blog_metadata} -{authors} + + Language models have shown impressive capabilities in the past few years by generating diverse and compelling text from human input prompts. However, what makes a "good" text is inherently hard to define as it is subjective and context dependent. There are many applications such as writing stories where you want creativity, pieces of informative text which should be truthful, or code snippets that we want to be executable. diff --git a/sagemaker-distributed-training-seq2seq.md b/sagemaker-distributed-training-seq2seq.md index 40107fc254..6809d2ea92 100644 --- a/sagemaker-distributed-training-seq2seq.md +++ b/sagemaker-distributed-training-seq2seq.md @@ -7,8 +7,8 @@ authors: # Distributed Training: Train BART/T5 for Summarization using 🤗 Transformers and Amazon SageMaker -{blog_metadata} -{authors} + + Open on Github diff --git a/sasha-luccioni-interview.md b/sasha-luccioni-interview.md index 365137511b..05cff81db8 100644 --- a/sasha-luccioni-interview.md +++ b/sasha-luccioni-interview.md @@ -7,8 +7,8 @@ authors:

Machine Learning Experts - Sasha Luccioni

-{blog_metadata} -{authors} + + ## 🤗 Welcome to Machine Learning Experts - Sasha Luccioni diff --git a/sb3.md b/sb3.md index ce642c6676..ed69ec2308 100644 --- a/sb3.md +++ b/sb3.md @@ -7,8 +7,8 @@ authors: # Welcome Stable-baselines3 to the Hugging Face Hub 🤗 -{blog_metadata} -{authors} + + At Hugging Face, we are contributing to the ecosystem for Deep Reinforcement Learning researchers and enthusiasts. That’s why we’re happy to announce that we integrated [Stable-Baselines3](https://github.com/DLR-RM/stable-baselines3) to the Hugging Face Hub. diff --git a/searching-the-hub.md b/searching-the-hub.md index 8293740ae6..613587b509 100644 --- a/searching-the-hub.md +++ b/searching-the-hub.md @@ -7,8 +7,8 @@ authors: # Supercharged Searching on the Hugging Face Hub -{blog_metadata} -{authors} + + Open In Colab diff --git a/sempre-health-eap-case-study.md b/sempre-health-eap-case-study.md index 527c86ec4f..694c3a81fe 100644 --- a/sempre-health-eap-case-study.md +++ b/sempre-health-eap-case-study.md @@ -7,8 +7,8 @@ authors:

How Sempre Health is leveraging the Expert Acceleration Program to accelerate their ML roadmap

-{blog_metadata} -{authors} + + 👋 Hello, friends! We recently sat down with [Swaraj Banerjee](https://www.linkedin.com/in/swarajbanerjee/) and [Larry Zhang](https://www.linkedin.com/in/larry-zhang-b58642a3/) from [Sempre Health](https://www.semprehealth.com/), a startup that brings behavior-based, dynamic pricing to Healthcare. They are doing some exciting work with machine learning and are leveraging our [Expert Acceleration Program](https://huggingface.co/support) to accelerate their ML roadmap. diff --git a/sentence-transformers-in-the-hub.md b/sentence-transformers-in-the-hub.md index 6148cf9111..74db4b1ade 100644 --- a/sentence-transformers-in-the-hub.md +++ b/sentence-transformers-in-the-hub.md @@ -7,8 +7,8 @@ authors: # Sentence Transformers in the Hugging Face Hub -{blog_metadata} -{authors} + + Over the past few weeks, we've built collaborations with many Open Source frameworks in the machine learning ecosystem. One that gets us particularly excited is Sentence Transformers. diff --git a/sentiment-analysis-fhe.md b/sentiment-analysis-fhe.md index e32070c7a8..0a3d575785 100644 --- a/sentiment-analysis-fhe.md +++ b/sentiment-analysis-fhe.md @@ -8,8 +8,8 @@ authors: # Sentiment Analysis on Encrypted Data with Homomorphic Encryption -{blog_metadata} -{authors} + + It is well-known that a sentiment analysis model determines whether a text is positive, negative, or neutral. However, this process typically requires access to unencrypted text, which can pose privacy concerns. diff --git a/sentiment-analysis-python.md b/sentiment-analysis-python.md index 03ca2403c9..6d1bcc848b 100644 --- a/sentiment-analysis-python.md +++ b/sentiment-analysis-python.md @@ -7,8 +7,8 @@ authors:

Getting Started with Sentiment Analysis using Python

-{blog_metadata} -{authors} + + diff --git a/sentiment-analysis-twitter.md b/sentiment-analysis-twitter.md index 581310b6ff..b0de3a518a 100644 --- a/sentiment-analysis-twitter.md +++ b/sentiment-analysis-twitter.md @@ -7,8 +7,8 @@ authors:

Getting Started with Sentiment Analysis on Twitter

-{blog_metadata} -{authors} + + diff --git a/series-c.md b/series-c.md index 869f01d712..51f9ae48f4 100644 --- a/series-c.md +++ b/series-c.md @@ -7,8 +7,8 @@ authors:

We Raised $100 Million for Open & Collaborative Machine Learning 🚀

-{blog_metadata} -{authors} + + Today we have some exciting news to share! Hugging Face has raised $100 Million in Series C funding 🔥🔥🔥 led by Lux Capital with major participations from Sequoia, Coatue and support of existing investors Addition, a_capital, SV Angel, Betaworks, AIX Ventures, Kevin Durant, Rich Kleiman from Thirty Five Ventures, Olivier Pomel (co-founder & CEO at Datadog) and more. diff --git a/setfit.md b/setfit.md index 164feca466..910ff5f2c0 100644 --- a/setfit.md +++ b/setfit.md @@ -12,8 +12,8 @@ authors:

SetFit: Efficient Few-Shot Learning Without Prompts

-{blog_metadata} -{authors} + + diff --git a/simple-considerations.md b/simple-considerations.md index f3838dfd00..dd7ca2e0b4 100644 --- a/simple-considerations.md +++ b/simple-considerations.md @@ -11,8 +11,8 @@ authors: # 🚧 Simple considerations for simple people building fancy neural networks -{blog_metadata} -{authors} + + As machine learning continues penetrating all aspects of the industry, neural networks have never been so hyped. For instance, models like GPT-3 have been all over social media in the past few weeks and continue to make headlines outside of tech news outlets with fear-mongering titles. diff --git a/skops.md b/skops.md index 92285056a5..11879cd821 100644 --- a/skops.md +++ b/skops.md @@ -9,8 +9,8 @@ authors: # Introducing Skops -{blog_metadata} -{authors} + + ## Introducing Skops diff --git a/snowball-fight.md b/snowball-fight.md index d28c49584d..bfcbfd4095 100644 --- a/snowball-fight.md +++ b/snowball-fight.md @@ -7,8 +7,8 @@ authors: # Introducing Snowball Fight ☃️, our First ML-Agents Environment -{blog_metadata} -{authors} + + diff --git a/spaces_3dmoljs.md b/spaces_3dmoljs.md index dbf99581fd..ea2815e49e 100644 --- a/spaces_3dmoljs.md +++ b/spaces_3dmoljs.md @@ -8,8 +8,8 @@ authors:

Visualize proteins on Hugging Face Spaces

-{blog_metadata} -{authors} + + In this post we will look at how we can visualize proteins on Hugging Face Spaces. diff --git a/spacy.md b/spacy.md index db974a2dff..f64931869f 100644 --- a/spacy.md +++ b/spacy.md @@ -9,8 +9,8 @@ authors: # Welcome spaCy to the Hugging Face Hub -{blog_metadata} -{authors} + + [spaCy](https://github.com/explosion/spaCy) is a popular library for advanced Natural Language Processing used widely across industry. spaCy makes it easy to use and train pipelines for tasks like named entity recognition, text classification, part of speech tagging and more, and lets you build powerful applications to process and analyze large volumes of text. diff --git a/stable_diffusion.md b/stable_diffusion.md index b1875e4374..8f70495b0c 100644 --- a/stable_diffusion.md +++ b/stable_diffusion.md @@ -10,8 +10,8 @@ authors: # Stable Diffusion with 🧨 Diffusers -{blog_metadata} -{authors} + + Open In Colab diff --git a/stable_diffusion_jax.md b/stable_diffusion_jax.md index 76d9c374bb..b67b57f083 100644 --- a/stable_diffusion_jax.md +++ b/stable_diffusion_jax.md @@ -8,8 +8,8 @@ authors: # 🧨 Stable Diffusion in JAX / Flax ! -{blog_metadata} -{authors} + + Open In Colab diff --git a/streamlit-spaces.md b/streamlit-spaces.md index 4b2d685c12..bce8f8923d 100644 --- a/streamlit-spaces.md +++ b/streamlit-spaces.md @@ -8,8 +8,8 @@ authors: # Hosting your Models and Datasets on Hugging Face Spaces using Streamlit -{blog_metadata} -{authors} + + diff --git a/summer-at-huggingface.md b/summer-at-huggingface.md index 825befb66b..e489a1c69f 100644 --- a/summer-at-huggingface.md +++ b/summer-at-huggingface.md @@ -8,8 +8,8 @@ authors: # Summer At Hugging Face 😎 -{blog_metadata} -{authors} + + Summer is now officially over and these last few months have been quite busy at Hugging Face. From new features in the Hub to research and Open Source development, our team has been working hard to empower the community through open and collaborative technology. diff --git a/supercharge-customer-service-with-machine-learning.md b/supercharge-customer-service-with-machine-learning.md index 7c0d55d42b..bc041dec02 100644 --- a/supercharge-customer-service-with-machine-learning.md +++ b/supercharge-customer-service-with-machine-learning.md @@ -7,8 +7,8 @@ authors: # Supercharged Customer Service with Machine Learning -{blog_metadata} -{authors} + + Open In Colab diff --git a/tapex.md b/tapex.md index 004f852aa4..02c0bed2c6 100644 --- a/tapex.md +++ b/tapex.md @@ -9,8 +9,8 @@ authors: # Efficient Table Pre-training without Real Data: An Introduction to TAPEX -{blog_metadata} -{authors} + + In recent years, language model pre-training has achieved great success via leveraging large-scale textual data. By employing pre-training tasks such as [masked language modeling](https://arxiv.org/abs/1810.04805), these models have demonstrated surprising performance on several downstream tasks. However, the dramatic gap between the pre-training task (e.g., language modeling) and the downstream task (e.g., table question answering) makes existing pre-training not efficient enough. In practice, we often need an *extremely large amount* of pre-training data to obtain promising improvement, even for [domain-adaptive pretraining](https://arxiv.org/abs/2004.02349). How might we design a pre-training task to close the gap, and thus accelerate pre-training? diff --git a/tensorflow-philosophy.md b/tensorflow-philosophy.md index f831d3c00b..e5fb0ce44b 100644 --- a/tensorflow-philosophy.md +++ b/tensorflow-philosophy.md @@ -7,8 +7,8 @@ authors: # Hugging Face's TensorFlow Philosophy -{blog_metadata} -{authors} + + ### Introduction diff --git a/tf-serving-vision.md b/tf-serving-vision.md index 13a6b3af4b..a8b6b5155d 100644 --- a/tf-serving-vision.md +++ b/tf-serving-vision.md @@ -8,8 +8,8 @@ authors: # Deploying TensorFlow Vision Models in Hugging Face with TF Serving -{blog_metadata} -{authors} + + Open In Colab diff --git a/tf-serving.md b/tf-serving.md index ff9addff30..98f9de7337 100644 --- a/tf-serving.md +++ b/tf-serving.md @@ -7,8 +7,8 @@ authors:

Faster TensorFlow models in Hugging Face Transformers

-{blog_metadata} -{authors} + + Open In Colab diff --git a/tf-xla-generate.md b/tf-xla-generate.md index bf9cf0ce3e..e0fe322b41 100644 --- a/tf-xla-generate.md +++ b/tf-xla-generate.md @@ -7,8 +7,8 @@ authors: # Faster Text Generation with TensorFlow and XLA -{blog_metadata} -{authors} + + TL;DR: Text Generation on 🤗 `transformers` using TensorFlow can now be compiled with XLA. It is up to 100x faster than before, and [even faster than PyTorch](https://huggingface.co/spaces/joaogante/tf_xla_generate_benchmarks) diff --git a/the-age-of-ml-as-code.md b/the-age-of-ml-as-code.md index 2bbc8b2e21..afc9a14bd3 100644 --- a/the-age-of-ml-as-code.md +++ b/the-age-of-ml-as-code.md @@ -8,8 +8,8 @@ authors: # The Age of Machine Learning As Code Has Arrived -{blog_metadata} -{authors} + + diff --git a/time-series-transformers.md b/time-series-transformers.md index a287cc4494..a9a9da3320 100644 --- a/time-series-transformers.md +++ b/time-series-transformers.md @@ -8,8 +8,8 @@ authors:

Probabilistic Time Series Forecasting with 🤗 Transformers

-{blog_metadata} -{authors} + + diff --git a/train-decision-transformers.md b/train-decision-transformers.md index 5ba59d2aff..cb29399362 100644 --- a/train-decision-transformers.md +++ b/train-decision-transformers.md @@ -8,8 +8,8 @@ authors: # Train your first Decision Transformer -{blog_metadata} -{authors} + + In a [previous post](https://huggingface.co/blog/decision-transformers), we announced the launch of Decision Transformers in the transformers library. This new technique of **using a Transformer as a Decision-making model** is getting increasingly popular. diff --git a/transformers-design-philosophy.md b/transformers-design-philosophy.md index d002b22bc7..7a5264b066 100644 --- a/transformers-design-philosophy.md +++ b/transformers-design-philosophy.md @@ -10,8 +10,8 @@ authors:
Designing open-source libraries for modern machine learning
-{blog_metadata} -{authors} + + ## 🤗 Transformers Design Philosophy diff --git a/us-national-ai-research-resource.md b/us-national-ai-research-resource.md index 0428172dcc..f0dda135ea 100644 --- a/us-national-ai-research-resource.md +++ b/us-national-ai-research-resource.md @@ -7,8 +7,8 @@ authors: # AI Policy @🤗: Comments on U.S. National AI Research Resource Interim Report -{blog_metadata} -{authors} + + In late June 2022, Hugging Face submitted a response to the White House Office of Science and Technology Policy and National Science Foundation’s Request for Information on a roadmap for implementing the National Artificial Intelligence Research Resource (NAIRR) Task Force’s interim report findings. As a platform working to democratize machine learning by empowering all backgrounds to contribute to AI, we strongly support NAIRR’s efforts. diff --git a/vision-transformers.md b/vision-transformers.md index dd0bccb0ed..f2a2c7b144 100644 --- a/vision-transformers.md +++ b/vision-transformers.md @@ -7,8 +7,8 @@ authors:

Deep Dive: Vision Transformers On Hugging Face Optimum Graphcore

-{blog_metadata} -{authors} + + This blog post will show how easy it is to fine-tune pre-trained Transformer models for your dataset using the Hugging Face Optimum library on Graphcore Intelligence Processing Units (IPUs). As an example, we will show a step-by-step guide and provide a notebook that takes a large, widely-used chest X-ray dataset and trains a vision transformer (ViT) model. diff --git a/vision_language_pretraining.md b/vision_language_pretraining.md index 825833f964..053a6e53b0 100644 --- a/vision_language_pretraining.md +++ b/vision_language_pretraining.md @@ -1,34 +1,15 @@ --- title: "A Dive into Vision-Language Models" thumbnail: /blog//assets/128_vision_language_pretraining/thumbnail.png +authors: +- adirik +- sayakpaul --- -

A Dive into Vision-Language Models

- -
- Published February 3, 2023. - - Update on GitHub - -
- -
- - -
- adirik - Alara Dirik -
- - - -
- sayakpaul - Sayak Paul -
- -
+# A Dive into Vision-Language Models + + Human learning is inherently multi-modal as jointly leveraging multiple senses helps us understand and analyze new information better. Unsurprisingly, recent advances in multi-modal learning take inspiration from the effectiveness of this process to create models that can process and link information using various modalities such as image, video, text, audio, body gestures, facial expressions, and physiological signals. diff --git a/vq-diffusion.md b/vq-diffusion.md index 58ae238c80..16c4ca5905 100644 --- a/vq-diffusion.md +++ b/vq-diffusion.md @@ -7,8 +7,8 @@ authors: # VQ-Diffusion -{blog_metadata} -{authors} + + Vector Quantized Diffusion (VQ-Diffusion) is a conditional latent diffusion model developed by the University of Science and Technology of China and Microsoft. Unlike most commonly studied diffusion models, VQ-Diffusion's noising and denoising processes operate on a quantized latent space, i.e., the latent space is composed of a discrete set of vectors. Discrete diffusion models are less explored than their continuous counterparts and offer an interesting point of comparison with autoregressive (AR) models. diff --git a/warm-starting-encoder-decoder.md b/warm-starting-encoder-decoder.md index f5f009d981..56b143ef97 100644 --- a/warm-starting-encoder-decoder.md +++ b/warm-starting-encoder-decoder.md @@ -7,8 +7,8 @@ authors: # Leveraging Pre-trained Language Model Checkpoints for Encoder-Decoder Models -{blog_metadata} -{authors} + + Open In Colab diff --git a/wav2vec2-with-ngram.md b/wav2vec2-with-ngram.md index 5afd7e9a24..4938526831 100644 --- a/wav2vec2-with-ngram.md +++ b/wav2vec2-with-ngram.md @@ -7,8 +7,8 @@ authors: # Boosting Wav2Vec2 with n-grams in 🤗 Transformers -{blog_metadata} -{authors} + + Open In Colab diff --git a/your-first-ml-project.md b/your-first-ml-project.md index 8b3329f52b..ec51d5322b 100644 --- a/your-first-ml-project.md +++ b/your-first-ml-project.md @@ -7,8 +7,8 @@ authors: # Liftoff! How to get started with your first ML project 🚀 -{blog_metadata} -{authors} + + People who are new to the Machine Learning world often run into two recurring stumbling blocks. The first is choosing the right library to learn, which can be daunting when there are so many to pick from. Even once you’ve settled on a library and gone through some tutorials, the next issue is coming up with your first big project and scoping it properly to maximize your learning. If you’ve run into those problems, and if you're looking for a new ML library to add to your toolkit, you're in the right place! diff --git a/zero-deepspeed-fairscale.md b/zero-deepspeed-fairscale.md index 42117f5837..0078f069c7 100644 --- a/zero-deepspeed-fairscale.md +++ b/zero-deepspeed-fairscale.md @@ -8,8 +8,8 @@ authors:

Fit More and Train Faster With ZeRO via DeepSpeed and FairScale

-{blog_metadata} -{authors} + + ##### A guest blog post by Hugging Face fellow Stas Bekman diff --git a/zero-shot-eval-on-the-hub.md b/zero-shot-eval-on-the-hub.md index 1c186c2484..e9553df6d1 100644 --- a/zero-shot-eval-on-the-hub.md +++ b/zero-shot-eval-on-the-hub.md @@ -11,8 +11,8 @@ authors: # Very Large Language Models and How to Evaluate Them -{blog_metadata} -{authors} + + Large language models can now be evaluated on zero-shot classification tasks with [Evaluation on the Hub](https://huggingface.co/spaces/autoevaluate/model-evaluator)!