From 2d74c9343b383e379b5e8774ee4ff54f35ee11c9 Mon Sep 17 00:00:00 2001 From: Julien Chaumond Date: Tue, 3 Oct 2023 12:08:37 +0200 Subject: [PATCH] No more magic comments (#1554) * no more magic comments * Also replace h1 by actual markdown * nit: remove extra space * Fix remaining

s * handling complex h1 heading * Update README.md cc @mishig25 --------- Co-authored-by: Mishig Davaadorj --- 1b-sentence-embeddings.md | 2 -- 3d-assets.md | 2 -- 4bit-transformers-bitsandbytes.md | 2 -- Llama2-for-non-engineers.md | 2 -- README.md | 8 ++------ accelerate-deepspeed.md | 4 +--- accelerate-large-models.md | 2 -- accelerate-library.md | 2 -- accelerate-transformers-with-inferentia2.md | 2 -- accelerated-inference.md | 3 +-- accelerating-pytorch.md | 2 -- agents-js.md | 2 -- ai-comic-factory.md | 2 -- ai-residency.md | 2 -- ai-webtv.md | 2 -- aivsai.md | 2 -- ambassadors.md | 2 -- annotated-diffusion.md | 2 -- arxiv.md | 2 -- asr-chunking.md | 2 -- assisted-generation.md | 2 -- audio-datasets.md | 2 -- audioldm2.md | 2 -- autoformer.md | 2 -- autonlp-prodigy.md | 4 +--- autotrain-image-classification.md | 2 -- aws-marketplace.md | 2 -- aws-partnership.md | 2 -- bert-101.md | 4 +--- bert-cpu-scaling-part-1.md | 2 -- bert-cpu-scaling-part-2.md | 2 -- bert-inferentia-sagemaker.md | 4 +--- bertopic.md | 4 +--- big-bird.md | 2 -- blip-2.md | 2 -- bloom-inference-optimization.md | 4 +--- bloom-inference-pytorch-scripts.md | 4 +--- bloom-megatron-deepspeed.md | 4 +--- bloom.md | 4 +--- bridgetower.md | 2 -- carbon-emissions-on-the-hub.md | 4 +--- chatbot-amd-gpu.md | 6 +----- chinese-language-blog.md | 4 +--- classification-use-cases.md | 2 -- clipseg-zero-shot.md | 2 -- cnil.md | 4 +--- codellama.md | 2 -- codeparrot.md | 4 +--- collaborative-training.md | 2 -- constrained-beam-search.md | 2 -- content-guidelines-update.md | 2 -- controlnet.md | 2 -- convert-transformers-to-onnx.md | 2 -- course-launch-event.md | 1 - cv_state.md | 2 -- data-measurements-tool.md | 2 -- databricks-case-study.md | 4 +--- datasets-docs-update.md | 2 -- decision-transformers.md | 2 -- dedup.md | 2 -- deep-learning-with-proteins.md | 2 -- deep-rl-a2c.md | 3 +-- deep-rl-dqn.md | 3 +-- deep-rl-intro.md | 3 +-- deep-rl-pg.md | 3 +-- deep-rl-ppo.md | 3 +-- deep-rl-q-part1.md | 3 +-- deep-rl-q-part2.md | 3 +-- deploy-deepfloydif-using-bentoml.md | 2 -- ...oy-hugging-face-models-easily-with-amazon-sagemaker.md | 1 - deploy-tfserving-kubernetes.md | 2 -- deploy-vertex-ai.md | 2 -- dialog-agents.md | 2 -- diffusers-2nd-month.md | 2 -- diffusers-coreml.md | 2 -- diffusers-turns-1.md | 2 -- diffusion-models-event.md | 2 -- document-ai.md | 2 -- dpo-trl.md | 2 -- dreambooth.md | 2 -- education.md | 2 -- elixir-bumblebee.md | 2 -- encoder-decoder.md | 4 +--- encrypted-llm.md | 2 -- ethical-charter-multimodal.md | 2 -- ethics-diffusers.md | 2 -- ethics-soc-1.md | 2 -- ethics-soc-2.md | 2 -- ethics-soc-3.md | 2 -- ethics-soc-4.md | 2 -- ethics-soc-5.md | 2 -- eu-ai-act-oss.md | 4 +--- eval-on-the-hub.md | 2 -- evaluating-llm-bias.md | 2 -- evaluating-mmlu-leaderboard.md | 2 -- falcon-180b.md | 2 -- falcon.md | 2 -- fast-diffusers-coreml.md | 2 -- fast-mac-diffusers.md | 2 -- fastai.md | 2 -- fasttext.md | 2 -- fellowship.md | 2 -- fetch-case-study.md | 4 +--- few-shot-learning-gpt-neo-and-inference-api.md | 2 -- fine-tune-clip-rsicd.md | 2 -- fine-tune-segformer.md | 2 -- fine-tune-vit.md | 2 -- fine-tune-wav2vec2-english.md | 2 -- fine-tune-whisper.md | 2 -- fine-tune-xlsr-wav2vec2.md | 2 -- fl-with-flower.md | 2 -- game-jam-first-edition-results.md | 2 -- game-jam.md | 3 +-- gaussian-splatting.md | 4 +--- generative-ai-models-on-intel-cpu.md | 2 -- getting-started-habana.md | 2 -- getting-started-with-embeddings.md | 2 -- gptj-sagemaker.md | 4 +--- gptq-integration.md | 2 -- gradio-blocks.md | 4 +--- gradio-joins-hf.md | 4 +--- gradio-spaces.md | 2 -- gradio.md | 2 -- graphcore-getting-started.md | 1 - graphcore-update.md | 2 -- graphcore.md | 2 -- habana-gaudi-2-benchmark.md | 2 -- habana-gaudi-2-bloom.md | 2 -- habana.md | 2 -- hardware-partners-program.md | 2 -- hf-bitsandbytes-integration.md | 2 -- hf-hub-glam-guide.md | 2 -- how-to-deploy-a-pipeline-to-google-clouds.md | 2 -- how-to-generate.md | 4 +--- how-to-train-sentence-transformers.md | 2 -- how-to-train.md | 4 +--- hub-duckdb.md | 2 -- hugging-face-endpoints-on-azure.md | 2 -- huggingface-and-amd.md | 2 -- huggingface-and-ibm.md | 2 -- huggy-lingo.md | 2 -- huggylingo.md | 2 -- idefics.md | 2 -- if.md | 2 -- image-search-datasets.md | 4 +--- image-similarity.md | 2 -- inference-endpoints-llm.md | 2 -- inference-endpoints.md | 2 -- inference-pro.md | 2 -- inference-update.md | 4 +--- infinity-cpu-performance.md | 4 +--- informer.md | 2 -- instruction-tuning-sd.md | 2 -- intel-sapphire-rapids-inference.md | 2 -- intel-sapphire-rapids.md | 7 +------ intel.md | 4 +--- interns-2023.md | 2 -- intro-graphml.md | 2 -- introducing-csearch.md | 4 +--- introducing-doi.md | 2 -- introducing-private-hub.md | 4 +--- japanese-stable-diffusion.md | 2 -- large-language-models.md | 2 -- lewis-tunstall-interview.md | 4 +--- livebook-app-deployment.md | 2 -- llama-sagemaker-benchmark.md | 2 -- llama2.md | 2 -- llm-leaderboard.md | 2 -- long-range-transformers.md | 2 -- lora.md | 2 -- mantis-case-study.md | 4 +--- mask2former.md | 2 -- 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 | 3 +-- ml-director-insights.md | 4 +--- ml-for-games-1.md | 3 +-- ml-for-games-2.md | 4 +--- ml-for-games-3.md | 4 +--- ml-for-games-4.md | 4 +--- ml-for-games-5.md | 4 +--- ml-web-games.md | 2 -- mms_adapters.md | 2 -- mnist-adversarial.md | 2 -- model-cards.md | 2 -- mteb.md | 4 +--- notebooks-hub.md | 4 +--- nystromformer.md | 4 +--- object-detection-leaderboard.md | 2 -- open_rail.md | 4 +--- openvino.md | 4 +--- opinion-classification-with-kili.md | 2 -- optimize-llm.md | 2 -- optimizing-bark.md | 2 -- optimum-inference.md | 2 -- optimum-onnxruntime-training.md | 2 -- os-llms.md | 4 +--- overview-quantization-transformers.md | 2 -- owkin-substra.md | 2 -- paddlepaddle.md | 2 -- panel-on-hugging-face.md | 2 -- password-git-deprecation.md | 2 -- peft.md | 4 +--- perceiver.md | 4 +--- playlist-generator.md | 2 -- policy-ntia-rfc.md | 4 +--- porting-fsmt.md | 4 +--- pretraining-bert.md | 2 -- pricing-update.md | 4 +--- pytorch-ddp-accelerate-transformers.md | 2 -- pytorch-fsdp.md | 4 +--- pytorch-xla.md | 4 +--- pytorch_block_sparse.md | 4 +--- ram-efficient-pytorch-fsdp.md | 2 -- ray-rag.md | 2 -- ray-tune.md | 2 -- red-teaming.md | 2 -- reformer.md | 4 +--- rlhf.md | 2 -- rocketmoney-case-study.md | 4 +--- run-musicgen-as-an-api.md | 4 +--- rwkv.md | 2 -- safecoder-vs-closed-source-code-assistants.md | 2 -- safecoder.md | 2 -- safetensors-security-audit.md | 2 -- sagemaker-distributed-training-seq2seq.md | 2 -- sagemaker-huggingface-llm.md | 2 -- sasha-luccioni-interview.md | 4 +--- sb3.md | 2 -- sd_distillation.md | 4 +--- searching-the-hub.md | 2 -- sempre-health-eap-case-study.md | 4 +--- sentence-transformers-in-the-hub.md | 2 -- sentiment-analysis-fhe.md | 2 -- sentiment-analysis-python.md | 4 +--- sentiment-analysis-twitter.md | 4 +--- series-c.md | 4 +--- setfit.md | 4 +--- simple-considerations.md | 2 -- skops.md | 2 -- snorkel-case-study.md | 4 +--- snowball-fight.md | 2 -- spaces_3dmoljs.md | 4 +--- spacy.md | 2 -- speecht5.md | 2 -- stable-diffusion-finetuning-intel.md | 2 -- stable-diffusion-inference-intel.md | 2 -- stable-diffusion-xl-coreml.md | 2 -- stable_diffusion.md | 2 -- stable_diffusion_jax.md | 2 -- stackllama.md | 2 -- starchat-alpha.md | 2 -- starcoder.md | 2 -- streamlit-spaces.md | 2 -- summer-at-huggingface.md | 2 -- supercharge-customer-service-with-machine-learning.md | 2 -- swift-coreml-llm.md | 2 -- t2i-sdxl-adapters.md | 2 -- tapex.md | 2 -- tensorflow-philosophy.md | 2 -- text-to-video.md | 4 +--- text-to-webapp.md | 2 -- tf-serving-vision.md | 2 -- tf-serving.md | 4 +--- tf-xla-generate.md | 2 -- tf_tpu.md | 2 -- the-age-of-ml-as-code.md | 2 -- time-series-transformers.md | 4 +--- train-decision-transformers.md | 2 -- train-optimize-sd-intel.md | 2 -- train-your-controlnet.md | 2 -- transformers-design-philosophy.md | 8 ++------ trl-ddpo.md | 2 -- trl-peft.md | 2 -- unity-api.md | 3 +-- unity-asr.md | 4 +--- unity-in-spaces.md | 3 +-- us-national-ai-research-resource.md | 2 -- using-ml-for-disasters.md | 2 -- vision-transformers.md | 4 +--- vision_language_pretraining.md | 2 -- vit-align.md | 2 -- vq-diffusion.md | 2 -- warm-starting-encoder-decoder.md | 2 -- wav2vec2-with-ngram.md | 2 -- writer-case-study.md | 4 +--- wuerstchen.md | 2 -- your-first-ml-project.md | 2 -- zero-deepspeed-fairscale.md | 4 +--- zero-shot-eval-on-the-hub.md | 2 -- zh/_policy-ntia-rfc.md | 3 +-- zh/accelerated-inference.md | 3 +-- zh/aivsai.md | 2 -- zh/assisted-generation.md | 2 -- zh/autoformer.md | 2 -- zh/blip-2.md | 2 -- zh/bloom-inference-optimization.md | 4 +--- zh/bloom-inference-pytorch-scripts.md | 2 -- zh/bloom-megatron-deepspeed.md | 4 +--- zh/bridgetower.md | 2 -- zh/chinese-language-blog.md | 4 +--- zh/codellama.md | 2 -- zh/constrained-beam-search.md | 2 -- zh/controlnet.md | 2 -- zh/cv_state.md | 2 -- zh/dedup.md | 2 -- zh/deploy-deepfloydif-using-bentoml.md | 2 -- zh/dialog-agents.md | 2 -- zh/diffusers-turns-1.md | 2 -- zh/document-ai.md | 2 -- zh/dpo-trl.md | 2 -- zh/dreambooth.md | 2 -- zh/elixir-bumblebee.md | 2 -- zh/encoder-decoder.md | 4 +--- zh/encrypted-llm.md | 2 -- zh/ethics-diffusers.md | 2 -- zh/ethics-soc-3.md | 2 -- zh/ethics-soc-4.md | 2 -- zh/evaluating-mmlu-leaderboard.md | 2 -- zh/falcon-180b.md | 2 -- zh/falcon.md | 2 -- zh/fine-tune-whisper.md | 2 -- zh/game-jam-first-edition-results.md | 2 -- zh/generative-ai-models-on-intel-cpu.md | 2 -- zh/getting-started-habana.md | 2 -- zh/gptq-integration.md | 2 -- zh/habana-gaudi-2-benchmark.md | 2 -- zh/habana-gaudi-2-bloom.md | 2 -- zh/hf-bitsandbytes-integration.md | 2 -- zh/how-to-generate.md | 4 +--- zh/idefics.md | 2 -- zh/if.md | 2 -- zh/image-similarity.md | 7 +------ zh/inference-endpoints-llm.md | 2 -- zh/inference-update.md | 4 +--- zh/informer.md | 2 -- zh/instruction-tuning-sd.md | 2 -- zh/intel-sapphire-rapids-inference.md | 2 -- zh/intel-sapphire-rapids.md | 2 -- zh/intro-graphml.md | 2 -- zh/introducing-csearch.md | 4 +--- zh/large-language-models.md | 2 -- zh/llama2.md | 2 -- zh/llm-leaderboard.md | 2 -- zh/lora.md | 2 -- zh/mask2former.md | 2 -- zh/megatron-training.md | 4 +--- zh/ml-for-games-1.md | 2 -- zh/ml-for-games-2.md | 2 -- zh/ml-for-games-3.md | 4 +--- zh/ml-for-games-4.md | 4 +--- zh/ml-for-games-5.md | 4 +--- zh/mms_adapters.md | 2 -- zh/optimizing-bark.md | 2 -- zh/optimum-onnxruntime-training.md | 2 -- zh/os-llms.md | 4 +--- zh/password-git-deprecation.md | 2 -- zh/peft.md | 2 -- zh/pytorch-ddp-accelerate-transformers.md | 2 -- zh/red-teaming.md | 2 -- zh/rlhf.md | 2 -- zh/rwkv.md | 2 -- zh/safecoder.md | 2 -- zh/sd_distillation.md | 4 +--- zh/setfit.md | 4 +--- zh/speecht5.md | 2 -- zh/stable-diffusion-finetuning-intel.md | 2 -- zh/stable-diffusion-inference-intel.md | 2 -- zh/stackllama.md | 2 -- zh/starchat-alpha.md | 2 -- zh/starcoder.md | 2 -- zh/t2i-sdxl-adapters.md | 2 -- zh/text-to-video.md | 4 +--- zh/time-series-transformers.md | 4 +--- zh/train-your-controlnet.md | 2 -- zh/transformers-design-philosophy.md | 8 ++------ zh/trl-peft.md | 2 -- zh/unity-api.md | 4 +--- zh/unity-asr.md | 4 +--- zh/unity-in-spaces.md | 2 -- zh/vision_language_pretraining.md | 2 -- zh/vit-align.md | 2 -- 384 files changed, 115 insertions(+), 879 deletions(-) diff --git a/1b-sentence-embeddings.md b/1b-sentence-embeddings.md index 5ad7e84fae..606f215e75 100644 --- a/1b-sentence-embeddings.md +++ b/1b-sentence-embeddings.md @@ -7,8 +7,6 @@ authors: # Train a Sentence Embedding Model with 1 Billion Training Pairs - - **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/3d-assets.md b/3d-assets.md index d1d0277ffc..c706f986db 100644 --- a/3d-assets.md +++ b/3d-assets.md @@ -7,8 +7,6 @@ authors: # Practical 3D Asset Generation: A Step-by-Step Guide - - ## Introduction diff --git a/4bit-transformers-bitsandbytes.md b/4bit-transformers-bitsandbytes.md index a2dbd79a9e..3d8257c49b 100644 --- a/4bit-transformers-bitsandbytes.md +++ b/4bit-transformers-bitsandbytes.md @@ -13,8 +13,6 @@ authors: # Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA - - LLMs are known to be large, and running or training them in consumer hardware is a huge challenge for users and accessibility. Our [LLM.int8 blogpost](https://huggingface.co/blog/hf-bitsandbytes-integration) showed how the techniques in the [LLM.int8 paper](https://arxiv.org/abs/2208.07339) were integrated in transformers using the `bitsandbytes` library. diff --git a/Llama2-for-non-engineers.md b/Llama2-for-non-engineers.md index f37fc9077e..4dfd92ac52 100644 --- a/Llama2-for-non-engineers.md +++ b/Llama2-for-non-engineers.md @@ -6,8 +6,6 @@ authors: - user: abhishek --- - - # Non-engineers guide: Train a LLaMA 2 chatbot diff --git a/README.md b/README.md index 66e178ccf4..e65b27edc9 100644 --- a/README.md +++ b/README.md @@ -29,19 +29,15 @@ authors: # Train your first Decision Transformer - - - 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: +When published, the Hub will insert the following UI elements right after the blogpost's main header (i.e. the line that starts with a single `#`, aka. the `

`): + - "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. diff --git a/accelerate-deepspeed.md b/accelerate-deepspeed.md index 7c89a8bd14..b3bceb1f73 100644 --- a/accelerate-deepspeed.md +++ b/accelerate-deepspeed.md @@ -6,10 +6,8 @@ authors: - user: sgugger --- -

Accelerate Large Model Training using DeepSpeed

+# Accelerate Large Model Training using DeepSpeed - - 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 0a25e0315e..56f4289022 100644 --- a/accelerate-large-models.md +++ b/accelerate-large-models.md @@ -7,8 +7,6 @@ authors: # How 🤗 Accelerate runs very large models thanks to PyTorch - - ## Load and run large models diff --git a/accelerate-library.md b/accelerate-library.md index d4f642baf0..d06c50b4fa 100644 --- a/accelerate-library.md +++ b/accelerate-library.md @@ -7,8 +7,6 @@ authors: # Introducing 🤗 Accelerate - - ## 🤗 Accelerate diff --git a/accelerate-transformers-with-inferentia2.md b/accelerate-transformers-with-inferentia2.md index a78f183c8f..e422b0fa01 100644 --- a/accelerate-transformers-with-inferentia2.md +++ b/accelerate-transformers-with-inferentia2.md @@ -8,8 +8,6 @@ authors: # Accelerating Hugging Face Transformers with AWS Inferentia2 - - diff --git a/accelerated-inference.md b/accelerated-inference.md index d9af2a7e55..ad6d017053 100644 --- a/accelerated-inference.md +++ b/accelerated-inference.md @@ -3,9 +3,8 @@ title: "How we sped up transformer inference 100x for 🤗 API customers" thumbnail: /blog/assets/09_accelerated_inference/thumbnail.png --- -

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

+# How we sped up transformer inference 100x for 🤗 API customers - 🤗 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 6953c28a56..f8bf3586d1 100644 --- a/accelerating-pytorch.md +++ b/accelerating-pytorch.md @@ -8,8 +8,6 @@ authors: # Accelerating PyTorch distributed fine-tuning with Intel technologies - - 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/agents-js.md b/agents-js.md index 8fb1208dcf..d232b691b4 100644 --- a/agents-js.md +++ b/agents-js.md @@ -7,8 +7,6 @@ authors: # Introducing Agents.js: Give tools to your LLMs using JavaScript - - We have recently been working on Agents.js at [huggingface.js](https://github.com/huggingface/huggingface.js/blob/main/packages/agents/README.md). It's a new library for giving tool access to LLMs from JavaScript in either the browser or the server. It ships with a few multi-modal tools out of the box and can easily be extended with your own tools and language models. diff --git a/ai-comic-factory.md b/ai-comic-factory.md index f2977c20a1..bf7e554be5 100644 --- a/ai-comic-factory.md +++ b/ai-comic-factory.md @@ -7,8 +7,6 @@ authors: # Deploying the AI Comic Factory using the Inference API - - We recently announced [Inference for PROs](https://huggingface.co/blog/inference-pro), our new offering that makes larger models accessible to a broader audience. This opportunity opens up new possibilities for running end-user applications using Hugging Face as a platform. diff --git a/ai-residency.md b/ai-residency.md index 51d3eb193e..6838bbaa98 100644 --- a/ai-residency.md +++ b/ai-residency.md @@ -7,8 +7,6 @@ authors: # Announcing the 🤗 AI Research Residency Program 🎉 🎉 🎉 - - 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/ai-webtv.md b/ai-webtv.md index 95e79bbf77..71ed84e6bb 100644 --- a/ai-webtv.md +++ b/ai-webtv.md @@ -7,8 +7,6 @@ authors: # Building an AI WebTV - - The AI WebTV is an experimental demo to showcase the latest advancements in automatic video and music synthesis. diff --git a/aivsai.md b/aivsai.md index 973563932f..40cbce9f8d 100644 --- a/aivsai.md +++ b/aivsai.md @@ -7,8 +7,6 @@ authors: --- # Introducing ⚔️ AI vs. AI ⚔️ a deep reinforcement learning multi-agents competition system - -
Thumbnail diff --git a/ambassadors.md b/ambassadors.md index d53397a427..a2a9e5e9f5 100644 --- a/ambassadors.md +++ b/ambassadors.md @@ -7,8 +7,6 @@ authors: # Student Ambassador Program’s call for applications is open! - - 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 4ee958b770..cd26f2005e 100644 --- a/annotated-diffusion.md +++ b/annotated-diffusion.md @@ -8,8 +8,6 @@ authors: # The Annotated Diffusion Model - - diff --git a/arxiv.md b/arxiv.md index c761bbbdc5..080acdba4e 100644 --- a/arxiv.md +++ b/arxiv.md @@ -9,8 +9,6 @@ authors: # Hugging Face Machine Learning Demos on arXiv - - 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 d482ab66c8..0315cf3a42 100644 --- a/asr-chunking.md +++ b/asr-chunking.md @@ -7,8 +7,6 @@ authors: # Making automatic speech recognition work on large files with Wav2Vec2 in 🤗 Transformers - - ``` Tl;dr: This post explains how to use the specificities of the Connectionist diff --git a/assisted-generation.md b/assisted-generation.md index 733e96a7c5..0b5dccb87a 100644 --- a/assisted-generation.md +++ b/assisted-generation.md @@ -7,8 +7,6 @@ authors: # Assisted Generation: a new direction toward low-latency text generation - - Large language models are all the rage these days, with many companies investing significant resources to scale them up and unlock new capabilities. However, as humans with ever-decreasing attention spans, we also dislike their slow response times. Latency is critical for a good user experience, and smaller models are often used despite their lower quality (e.g. in [code completion](https://ai.googleblog.com/2022/07/ml-enhanced-code-completion-improves.html)). diff --git a/audio-datasets.md b/audio-datasets.md index 0bea43158a..27d0de4919 100644 --- a/audio-datasets.md +++ b/audio-datasets.md @@ -7,8 +7,6 @@ authors: # A Complete Guide to Audio Datasets - - diff --git a/audioldm2.md b/audioldm2.md index b48d245a46..1a1214df2d 100644 --- a/audioldm2.md +++ b/audioldm2.md @@ -7,8 +7,6 @@ authors: # AudioLDM 2, but faster ⚡️ - - Open In Colab diff --git a/autoformer.md b/autoformer.md index d25e308ded..efc2c92f9e 100644 --- a/autoformer.md +++ b/autoformer.md @@ -10,8 +10,6 @@ authors: # Yes, Transformers are Effective for Time Series Forecasting (+ Autoformer) - - diff --git a/autonlp-prodigy.md b/autonlp-prodigy.md index aa89c55643..32bfa02145 100644 --- a/autonlp-prodigy.md +++ b/autonlp-prodigy.md @@ -5,10 +5,8 @@ authors: - user: abhishek --- -

Active Learning with AutoNLP and Prodigy

+# Active Learning with AutoNLP and Prodigy - - 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 795ce1e811..2903b3f7ef 100644 --- a/autotrain-image-classification.md +++ b/autotrain-image-classification.md @@ -7,8 +7,6 @@ authors: # Image Classification with AutoTrain - - diff --git a/aws-marketplace.md b/aws-marketplace.md index 25a470bf0f..f39a76e27f 100644 --- a/aws-marketplace.md +++ b/aws-marketplace.md @@ -9,8 +9,6 @@ authors: # Hugging Face Platform on the AWS Marketplace: Pay with your AWS Account - - The [Hugging Face Platform](https://aws.amazon.com/marketplace/pp/prodview-n6vsyhdjkfng2) has landed on the AWS Marketplace. Starting today, you can subscribe to the Hugging Face Platform through AWS Marketplace to pay for your Hugging Face usage directly with your AWS account. This new integrated billing method makes it easy to manage payment for usage of all our managed services by all members of your organization, including Inference Endpoints, Spaces Hardware Upgrades, and AutoTrain to easily train, test and deploy the most popular machine learning models like Llama 2, StarCoder, or BERT. diff --git a/aws-partnership.md b/aws-partnership.md index b7e1af6d98..0d098c40b5 100644 --- a/aws-partnership.md +++ b/aws-partnership.md @@ -9,8 +9,6 @@ authors: # Hugging Face and AWS partner to make AI more accessible - - It’s time to make AI open and accessible to all. That’s the goal of this expanded long-term strategic partnership between Hugging Face and Amazon Web Services (AWS). Together, the two leaders aim to accelerate the availability of next-generation machine learning models by making them more accessible to the machine learning community and helping developers achieve the highest performance at the lowest cost. diff --git a/bert-101.md b/bert-101.md index 755ac37261..dd5e20754a 100644 --- a/bert-101.md +++ b/bert-101.md @@ -5,10 +5,8 @@ authors: - user: britneymuller --- -

BERT 101 🤗 State Of The Art NLP Model Explained

+# BERT 101 🤗 State Of The Art NLP Model Explained - - diff --git a/bert-cpu-scaling-part-1.md b/bert-cpu-scaling-part-1.md index 65bc1058f8..6bf7d354af 100644 --- a/bert-cpu-scaling-part-1.md +++ b/bert-cpu-scaling-part-1.md @@ -19,8 +19,6 @@ 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 01c2de3a57..49a9dc0b8d 100644 --- a/bert-cpu-scaling-part-2.md +++ b/bert-cpu-scaling-part-2.md @@ -9,8 +9,6 @@ authors: # Scaling up BERT-like model Inference on modern CPU - Part 2 - - diff --git a/bert-inferentia-sagemaker.md b/bert-inferentia-sagemaker.md index 1250500b04..189dc9fd73 100644 --- a/bert-inferentia-sagemaker.md +++ b/bert-inferentia-sagemaker.md @@ -5,10 +5,8 @@ authors: - user: philschmid --- -

Accelerate BERT inference with Hugging Face Transformers and AWS Inferentia

+# Accelerate BERT inference with Hugging Face Transformers and AWS Inferentia - - diff --git a/bertopic.md b/bertopic.md index c5b6ff76da..2fbdab9ac9 100644 --- a/bertopic.md +++ b/bertopic.md @@ -7,10 +7,8 @@ authors: - user: davanstrien --- -

Introducing BERTopic Integration with the Hugging Face Hub

+# Introducing BERTopic Integration with the Hugging Face Hub - - [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg 'open in colab')](https://colab.research.google.com/#fileId=https://huggingface.co/spaces/davanstrien/blog_notebooks/blob/main/BERTopic_hub_starter.ipynb) diff --git a/big-bird.md b/big-bird.md index 956c53ae31..e76a4bd939 100644 --- a/big-bird.md +++ b/big-bird.md @@ -7,8 +7,6 @@ authors: # Understanding BigBird's Block Sparse Attention - - ## Introduction diff --git a/blip-2.md b/blip-2.md index bcc2a7d7f7..a5e6f8e7d3 100644 --- a/blip-2.md +++ b/blip-2.md @@ -8,8 +8,6 @@ authors: # Zero-shot image-to-text generation with BLIP-2 - - This guide introduces [BLIP-2](https://huggingface.co/docs/transformers/main/en/model_doc/blip-2) from Salesforce Research that enables a suite of state-of-the-art visual-language models that are now available in [🤗 Transformers](https://huggingface.co/transformers). diff --git a/bloom-inference-optimization.md b/bloom-inference-optimization.md index c4f57c2aff..93974fe922 100644 --- a/bloom-inference-optimization.md +++ b/bloom-inference-optimization.md @@ -5,9 +5,7 @@ authors: - user: Narsil --- -

Optimization story: Bloom inference

- - +# Optimization story: Bloom inference 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 e3720257c4..4dcd3ecc86 100644 --- a/bloom-inference-pytorch-scripts.md +++ b/bloom-inference-pytorch-scripts.md @@ -6,10 +6,8 @@ authors: - user: sgugger --- -

Incredibly Fast BLOOM Inference with DeepSpeed and Accelerate

+# Incredibly Fast BLOOM Inference with DeepSpeed and Accelerate - - 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 94c54ae3c1..3a6a2886a5 100644 --- a/bloom-megatron-deepspeed.md +++ b/bloom-megatron-deepspeed.md @@ -5,10 +5,8 @@ authors: - user: stas --- -

The Technology Behind BLOOM Training

+# The Technology Behind BLOOM Training - - diff --git a/bloom.md b/bloom.md index 4c58a02960..2bddc737e9 100644 --- a/bloom.md +++ b/bloom.md @@ -6,10 +6,8 @@ authors: --- -

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

+# 🌸 Introducing The World's Largest Open Multilingual Language Model: BLOOM 🌸 - - diff --git a/bridgetower.md b/bridgetower.md index 4b6c3d0409..8f86fd8793 100644 --- a/bridgetower.md +++ b/bridgetower.md @@ -9,8 +9,6 @@ authors: # Accelerating Vision-Language Models: BridgeTower on Habana Gaudi2 - - *Update (29/08/2023): A benchmark on H100 was added to this blog post. Also, all performance numbers have been updated with newer versions of software.* diff --git a/carbon-emissions-on-the-hub.md b/carbon-emissions-on-the-hub.md index 38ecd8a702..57ecbe5936 100644 --- a/carbon-emissions-on-the-hub.md +++ b/carbon-emissions-on-the-hub.md @@ -7,10 +7,8 @@ authors: - user: nateraw --- -

CO2 Emissions and the 🤗 Hub: Leading the Charge

+# CO2 Emissions and the 🤗 Hub: Leading the Charge - - ## What are CO2 Emissions and why are they important? diff --git a/chatbot-amd-gpu.md b/chatbot-amd-gpu.md index 408928c504..e29c6863cb 100644 --- a/chatbot-amd-gpu.md +++ b/chatbot-amd-gpu.md @@ -6,11 +6,7 @@ authors: guest: true --- -

-Run a Chatgpt-like Chatbot on a Single GPU with ROCm

- - - +# Run a Chatgpt-like Chatbot on a Single GPU with ROCm ## Introduction diff --git a/chinese-language-blog.md b/chinese-language-blog.md index a64c7e5a88..611c44ac25 100644 --- a/chinese-language-blog.md +++ b/chinese-language-blog.md @@ -9,10 +9,8 @@ authors: guest: true --- -

Introducing HuggingFace blog for Chinese speakers: Fostering Collaboration with the Chinese AI community

+# Introducing HuggingFace blog for Chinese speakers: Fostering Collaboration with the Chinese AI community - - ## Welcome to our blog for Chinese speakers! diff --git a/classification-use-cases.md b/classification-use-cases.md index c278625127..97a5479ccf 100644 --- a/classification-use-cases.md +++ b/classification-use-cases.md @@ -14,8 +14,6 @@ authors: ## The Success Story of Witty Works with the Hugging Face Expert Acceleration Program. - - _If you're interested in building ML solutions faster, visit the [Expert Acceleration Program](https://huggingface.co/support?utm_source=blog-post&utm_medium=blog-post&utm_campaign=blog-post-classification-use-case) landing page and contact us [here](https://huggingface.co/support?utm_source=blog-post&utm_medium=blog-post&utm_campaign=blog-post-classification-use-case#form)!_ diff --git a/clipseg-zero-shot.md b/clipseg-zero-shot.md index a6a774883e..ab1fd9b6ec 100644 --- a/clipseg-zero-shot.md +++ b/clipseg-zero-shot.md @@ -9,8 +9,6 @@ authors: # Zero-shot image segmentation with CLIPSeg - - diff --git a/cnil.md b/cnil.md index dba4abf0af..c9c29dd561 100644 --- a/cnil.md +++ b/cnil.md @@ -8,10 +8,8 @@ authors: - user: Ima1 --- -

Hugging Face Selected for the French Data Protection Agency Enhanced Support Program

+# Hugging Face Selected for the French Data Protection Agency Enhanced Support Program - - *This blog post was originally published on [LinkedIn on 05/15/2023](https://www.linkedin.com/pulse/accompagnement-renforc%25C3%25A9-de-la-cnil-et-protection-des-donn%25C3%25A9es/)* diff --git a/codellama.md b/codellama.md index 69cd0422d3..c7e9228cde 100644 --- a/codellama.md +++ b/codellama.md @@ -14,8 +14,6 @@ authors: # Code Llama: Llama 2 learns to code - - ## Introduction diff --git a/codeparrot.md b/codeparrot.md index 4a1f916a90..92eea7067a 100644 --- a/codeparrot.md +++ b/codeparrot.md @@ -5,10 +5,8 @@ authors: - user: leandro --- -

Training CodeParrot 🦜 from Scratch

+# Training CodeParrot 🦜 from Scratch - - 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 4bb10f18be..f68ca2236a 100644 --- a/collaborative-training.md +++ b/collaborative-training.md @@ -9,8 +9,6 @@ authors: # Deep Learning over the Internet: Training Language Models Collaboratively - - With the additional help of Quentin Lhoest and Sylvain Lesage. diff --git a/constrained-beam-search.md b/constrained-beam-search.md index 1038882226..3e0eddcb6b 100644 --- a/constrained-beam-search.md +++ b/constrained-beam-search.md @@ -8,8 +8,6 @@ authors: # Guiding Text Generation with Constrained Beam Search in 🤗 Transformers - - Open In Colab diff --git a/content-guidelines-update.md b/content-guidelines-update.md index 01bb8c8d3f..1724524796 100644 --- a/content-guidelines-update.md +++ b/content-guidelines-update.md @@ -7,8 +7,6 @@ authors: # Announcing our new Community Policy - - As a community-driven platform that aims to advance Open, Collaborative, and Responsible Machine Learning, we are thrilled to support and maintain a welcoming space for our entire community! In support of this goal, we've updated our [Content Policy](https://huggingface.co/content-guidelines). diff --git a/controlnet.md b/controlnet.md index c9b1dc4489..43d8e94d90 100644 --- a/controlnet.md +++ b/controlnet.md @@ -9,8 +9,6 @@ authors: # Ultra fast ControlNet with 🧨 Diffusers - - diff --git a/convert-transformers-to-onnx.md b/convert-transformers-to-onnx.md index 3b1212eb2f..8352893911 100644 --- a/convert-transformers-to-onnx.md +++ b/convert-transformers-to-onnx.md @@ -6,8 +6,6 @@ authors: --- # Convert Transformers to ONNX with Hugging Face Optimum - - 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 53e20a3025..4846bb9f28 100644 --- a/course-launch-event.md +++ b/course-launch-event.md @@ -7,7 +7,6 @@ authors: # Course Launch Community Event - 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 ab1524a5a4..842e00128f 100644 --- a/cv_state.md +++ b/cv_state.md @@ -7,8 +7,6 @@ authors: # The State of Computer Vision at Hugging Face 🤗 - - 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 02d84edb8a..f954256d83 100644 --- a/data-measurements-tool.md +++ b/data-measurements-tool.md @@ -9,8 +9,6 @@ authors: # Introducing the 🤗 Data Measurements Tool: an Interactive Tool for Looking at Datasets - - diff --git a/databricks-case-study.md b/databricks-case-study.md index 3bf605e9a1..655f9f1314 100644 --- a/databricks-case-study.md +++ b/databricks-case-study.md @@ -8,10 +8,8 @@ authors: guest: true --- -

Databricks ❤️ Hugging Face: up to 40% faster training and tuning of Large Language Models

+# Databricks ❤️ Hugging Face: up to 40% faster training and tuning of Large Language Models - - Generative AI has been taking the world by storm. As the data and AI company, we have been on this journey with the release of the open source large language model [Dolly](https://huggingface.co/databricks/dolly-v2-12b), as well as the internally crowdsourced dataset licensed for research and commercial use that we used to fine-tune it, the [databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k). Both the model and dataset are available on Hugging Face. We’ve learned a lot throughout this process, and today we’re excited to announce our first of many official commits to the Hugging Face codebase that allows users to easily create a Hugging Face Dataset from an Apache Spark™ dataframe. diff --git a/datasets-docs-update.md b/datasets-docs-update.md index 31177cc2fa..785be719cd 100644 --- a/datasets-docs-update.md +++ b/datasets-docs-update.md @@ -7,8 +7,6 @@ authors: # Introducing new audio and vision documentation in 🤗 Datasets - - 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 84bdfd4eb5..783c5c41d6 100644 --- a/decision-transformers.md +++ b/decision-transformers.md @@ -8,8 +8,6 @@ authors: # Introducing Decision Transformers on Hugging Face 🤗 - - 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/dedup.md b/dedup.md index 528065c684..363064d63a 100644 --- a/dedup.md +++ b/dedup.md @@ -7,8 +7,6 @@ authors: # Large-scale Near-deduplication Behind BigCode - - ## Intended Audience diff --git a/deep-learning-with-proteins.md b/deep-learning-with-proteins.md index cdc0271add..e0eacd58a5 100644 --- a/deep-learning-with-proteins.md +++ b/deep-learning-with-proteins.md @@ -7,8 +7,6 @@ authors: # Deep Learning With Proteins - - 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 9e13e75912..3b152590de 100644 --- a/deep-rl-a2c.md +++ b/deep-rl-a2c.md @@ -5,10 +5,9 @@ authors: - user: ThomasSimonini --- -

Advantage Actor Critic (A2C)

+# Advantage Actor Critic (A2C)

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

- ⚠️ A **new updated version of this article is available here** 👉 [https://huggingface.co/deep-rl-course/unit1/introduction](https://huggingface.co/deep-rl-course/unit6/introduction) diff --git a/deep-rl-dqn.md b/deep-rl-dqn.md index 775481be99..b5de20c923 100644 --- a/deep-rl-dqn.md +++ b/deep-rl-dqn.md @@ -6,10 +6,9 @@ authors: --- -

Deep Q-Learning with Space Invaders

+# Deep Q-Learning with Space Invaders

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

- diff --git a/deep-rl-intro.md b/deep-rl-intro.md index acdc9cc2e3..f74800bd26 100644 --- a/deep-rl-intro.md +++ b/deep-rl-intro.md @@ -7,10 +7,9 @@ authors: --- -

An Introduction to Deep Reinforcement Learning

+# An Introduction to Deep Reinforcement Learning

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

- diff --git a/deep-rl-pg.md b/deep-rl-pg.md index cd62882878..d346005ba5 100644 --- a/deep-rl-pg.md +++ b/deep-rl-pg.md @@ -6,10 +6,9 @@ authors: --- -

Policy Gradient with PyTorch

+# Policy Gradient with PyTorch

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

- diff --git a/deep-rl-ppo.md b/deep-rl-ppo.md index 571b77bc2b..6bef78c4eb 100644 --- a/deep-rl-ppo.md +++ b/deep-rl-ppo.md @@ -6,10 +6,9 @@ authors: --- -

Proximal Policy Optimization (PPO)

+# Proximal Policy Optimization (PPO)

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

- diff --git a/deep-rl-q-part1.md b/deep-rl-q-part1.md index 486b04d35c..363cb83767 100644 --- a/deep-rl-q-part1.md +++ b/deep-rl-q-part1.md @@ -6,10 +6,9 @@ authors: --- -

An Introduction to Q-Learning Part 1

+# An Introduction to Q-Learning Part 1

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

- diff --git a/deep-rl-q-part2.md b/deep-rl-q-part2.md index 7bbc5563b9..d5d7f827cf 100644 --- a/deep-rl-q-part2.md +++ b/deep-rl-q-part2.md @@ -6,10 +6,9 @@ authors: --- -

An Introduction to Q-Learning Part 2/2

+# An Introduction to Q-Learning Part 2/2

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

- diff --git a/deploy-deepfloydif-using-bentoml.md b/deploy-deepfloydif-using-bentoml.md index 32d88aa40f..abe5491bca 100644 --- a/deploy-deepfloydif-using-bentoml.md +++ b/deploy-deepfloydif-using-bentoml.md @@ -10,8 +10,6 @@ authors: # Deploying Hugging Face Models with BentoML: DeepFloyd IF in Action - - Hugging Face provides a Hub platform that allows you to upload, share, and deploy your models with ease. It saves developers the time and computational resources required to train models from scratch. However, deploying models in a real-world production environment or in a cloud-native way can still present challenges. diff --git a/deploy-hugging-face-models-easily-with-amazon-sagemaker.md b/deploy-hugging-face-models-easily-with-amazon-sagemaker.md index 5ccf1b276a..511b8482c0 100644 --- a/deploy-hugging-face-models-easily-with-amazon-sagemaker.md +++ b/deploy-hugging-face-models-easily-with-amazon-sagemaker.md @@ -5,7 +5,6 @@ thumbnail: /blog/assets/17_the_partnership_amazon_sagemaker_and_hugging_face/thu hugging-face-and-aws-logo - # **Deploy Hugging Face models easily with Amazon SageMaker 🏎** diff --git a/deploy-tfserving-kubernetes.md b/deploy-tfserving-kubernetes.md index 17533d4d55..531d010836 100644 --- a/deploy-tfserving-kubernetes.md +++ b/deploy-tfserving-kubernetes.md @@ -10,8 +10,6 @@ authors: # Deploying 🤗 ViT on Kubernetes with TF Serving - - # Introduction diff --git a/deploy-vertex-ai.md b/deploy-vertex-ai.md index 5dc5358c12..80094da5a7 100644 --- a/deploy-vertex-ai.md +++ b/deploy-vertex-ai.md @@ -10,8 +10,6 @@ authors: # Deploying 🤗 ViT on Vertex AI - - Open In Colab diff --git a/dialog-agents.md b/dialog-agents.md index 4a2bcad3e8..ecc57c2556 100644 --- a/dialog-agents.md +++ b/dialog-agents.md @@ -12,8 +12,6 @@ authors: # What Makes a Dialog Agent Useful? ## The techniques behind ChatGPT: RLHF, IFT, CoT, Red teaming, and more - - _This article has been translated to Chinese [简体中文](https://mp.weixin.qq.com/s/Xd5VtRP-ziH-PYFOci65Hg)_. diff --git a/diffusers-2nd-month.md b/diffusers-2nd-month.md index e3701bf177..5182658a07 100644 --- a/diffusers-2nd-month.md +++ b/diffusers-2nd-month.md @@ -7,8 +7,6 @@ authors: # What's new in Diffusers? 🎨 - - 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 53d3a6bf21..99c8570146 100644 --- a/diffusers-coreml.md +++ b/diffusers-coreml.md @@ -7,8 +7,6 @@ authors: # Using Stable Diffusion with Core ML on Apple Silicon - - Thanks to Apple engineers, you can now run Stable Diffusion on Apple Silicon using Core ML! diff --git a/diffusers-turns-1.md b/diffusers-turns-1.md index d0c0c082cc..d8ac908aab 100644 --- a/diffusers-turns-1.md +++ b/diffusers-turns-1.md @@ -9,8 +9,6 @@ authors: # Happy 1st anniversary 🤗 Diffusers! - - 🤗 Diffusers is happy to celebrate its first anniversary! It has been an exciting year, and we're proud and grateful for how far we've come thanks to our community and open-source contributors. Last year, text-to-image models like DALL-E 2, Imagen, and Stable Diffusion captured the world's attention with their ability to generate stunningly photorealistic images from text, sparking a massive surge of interest and development in generative AI. But access to these powerful models was limited. diff --git a/diffusion-models-event.md b/diffusion-models-event.md index 3089c9d437..785619f1fc 100644 --- a/diffusion-models-event.md +++ b/diffusion-models-event.md @@ -8,8 +8,6 @@ authors: # Diffusion Models Live Event - - 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 572c0fd97a..4f7c40de22 100644 --- a/document-ai.md +++ b/document-ai.md @@ -10,8 +10,6 @@ authors: # Accelerating Document AI - - 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/dpo-trl.md b/dpo-trl.md index 4871309cc3..09715d9531 100644 --- a/dpo-trl.md +++ b/dpo-trl.md @@ -9,8 +9,6 @@ authors: # Fine-tune Llama 2 with DPO - - ## Introduction diff --git a/dreambooth.md b/dreambooth.md index c5354723c0..7f04cded01 100644 --- a/dreambooth.md +++ b/dreambooth.md @@ -10,8 +10,6 @@ authors: # Training Stable Diffusion with Dreambooth using 🧨 Diffusers - - [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 3f1d32fc46..78627260d5 100644 --- a/education.md +++ b/education.md @@ -7,8 +7,6 @@ authors: # Introducing Hugging Face for Education 🤗 - - 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 bb39055bcf..2f34e35649 100644 --- a/elixir-bumblebee.md +++ b/elixir-bumblebee.md @@ -8,8 +8,6 @@ authors: # From GPT2 to Stable Diffusion: Hugging Face arrives to the Elixir community - - 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 f45fa7c72b..88d4ae50f1 100644 --- a/encoder-decoder.md +++ b/encoder-decoder.md @@ -5,10 +5,8 @@ authors: - user: patrickvonplaten --- -

Transformers-based Encoder-Decoder Models

+# Transformers-based Encoder-Decoder Models - - Open In Colab diff --git a/encrypted-llm.md b/encrypted-llm.md index abc6dc972c..12355b7f57 100644 --- a/encrypted-llm.md +++ b/encrypted-llm.md @@ -10,8 +10,6 @@ authors: # Towards Encrypted Large Language Models with FHE - - Large Language Models (LLM) have recently been proven as reliable tools for improving productivity in many areas such as programming, content creation, text analysis, web search, and distance learning. diff --git a/ethical-charter-multimodal.md b/ethical-charter-multimodal.md index 2182fe9015..0e45603439 100644 --- a/ethical-charter-multimodal.md +++ b/ethical-charter-multimodal.md @@ -20,8 +20,6 @@ authors: ## Ethical charter - Multimodal project - - ## Purpose of the ethical charter diff --git a/ethics-diffusers.md b/ethics-diffusers.md index 39b04bfa49..73744989d8 100644 --- a/ethics-diffusers.md +++ b/ethics-diffusers.md @@ -7,8 +7,6 @@ authors: # Ethical guidelines for developing the Diffusers library - - We are on a journey to make our libraries more responsible, one commit at a time! As part of the [Diffusers library documentation](https://huggingface.co/docs/diffusers/main/en/index), we are proud to announce the publication of an [ethical framework](https://huggingface.co/docs/diffusers/main/en/conceptual/ethical_guidelines). diff --git a/ethics-soc-1.md b/ethics-soc-1.md index 212653df95..b1064d1d9a 100644 --- a/ethics-soc-1.md +++ b/ethics-soc-1.md @@ -7,8 +7,6 @@ authors: # Ethics and Society Newsletter #1 - - Hello, world! diff --git a/ethics-soc-2.md b/ethics-soc-2.md index 72ba1d6cfa..e3f59d86f6 100644 --- a/ethics-soc-2.md +++ b/ethics-soc-2.md @@ -7,8 +7,6 @@ authors: # Machine Learning in development: Let's talk about bias! - - _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/ethics-soc-3.md b/ethics-soc-3.md index 13d803fdef..21d828da33 100644 --- a/ethics-soc-3.md +++ b/ethics-soc-3.md @@ -12,8 +12,6 @@ authors: # Ethics and Society Newsletter #3: Ethical Openness at Hugging Face - - ## Mission: Open and Good ML In our mission to democratize good machine learning (ML), we examine how supporting ML community work also empowers examining and preventing possible harms. Open development and science decentralizes power so that many people can collectively work on AI that reflects their needs and values. While [openness enables broader perspectives to contribute to research and AI overall, it faces the tension of less risk control](https://arxiv.org/abs/2302.04844). diff --git a/ethics-soc-4.md b/ethics-soc-4.md index 4e60963de7..3605272106 100644 --- a/ethics-soc-4.md +++ b/ethics-soc-4.md @@ -14,8 +14,6 @@ authors: # Ethics and Society Newsletter #4: Bias in Text-to-Image Models - - **TL;DR: We need better ways of evaluating bias in text-to-image models** diff --git a/ethics-soc-5.md b/ethics-soc-5.md index 446407d37c..071744fa27 100644 --- a/ethics-soc-5.md +++ b/ethics-soc-5.md @@ -10,8 +10,6 @@ authors: # Ethics and Society Newsletter #5: Hugging Face Goes To Washington and Other Summer 2023 Musings - - One of the most important things to know about “ethics” in AI is that it has to do with **values**. Ethics doesn’t tell you what’s right or wrong, it provides a vocabulary of values – transparency, safety, justice – and frameworks to prioritize among them. This summer, we were able to take our understanding of values in AI to legislators in the E.U., U.K., and U.S., to help shape the future of AI regulation. This is where ethics shines: helping carve out a path forward when laws are not yet in place. diff --git a/eu-ai-act-oss.md b/eu-ai-act-oss.md index 4c4d0ca4e5..8d938e7258 100644 --- a/eu-ai-act-oss.md +++ b/eu-ai-act-oss.md @@ -5,10 +5,8 @@ authors: - user: yjernite --- -

AI Policy @🤗: Open ML Considerations in the EU AI Act

+# AI Policy @🤗: Open ML Considerations in the EU AI Act - - Like everyone else in Machine Learning, we’ve been following the EU AI Act closely at Hugging Face. It’s a ground-breaking piece of legislation that is poised to shape how democratic inputs interact with AI technology development around the world. diff --git a/eval-on-the-hub.md b/eval-on-the-hub.md index c08e4d262b..daa8f6e8fa 100644 --- a/eval-on-the-hub.md +++ b/eval-on-the-hub.md @@ -15,8 +15,6 @@ authors: # Announcing Evaluation on the Hub - - 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 633d63c1ba..7bf72227f5 100644 --- a/evaluating-llm-bias.md +++ b/evaluating-llm-bias.md @@ -11,8 +11,6 @@ authors: # Evaluating Language Model Bias with 🤗 Evaluate - - 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/evaluating-mmlu-leaderboard.md b/evaluating-mmlu-leaderboard.md index 11fc014c08..aaabf3ce93 100644 --- a/evaluating-mmlu-leaderboard.md +++ b/evaluating-mmlu-leaderboard.md @@ -10,8 +10,6 @@ authors: # What's going on with the Open LLM Leaderboard? - - Recently an interesting discussion arose on Twitter following the release of [**Falcon 🦅**](https://huggingface.co/tiiuae/falcon-40b) and its addition to the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard), a public leaderboard comparing open access large language models. diff --git a/falcon-180b.md b/falcon-180b.md index 2fba5d6138..94389e30f7 100644 --- a/falcon-180b.md +++ b/falcon-180b.md @@ -11,8 +11,6 @@ authors: # Spread Your Wings: Falcon 180B is here - - ## Introduction diff --git a/falcon.md b/falcon.md index d18f952d32..0c447398aa 100644 --- a/falcon.md +++ b/falcon.md @@ -14,8 +14,6 @@ authors: # The Falcon has landed in the Hugging Face ecosystem - - ## Introduction diff --git a/fast-diffusers-coreml.md b/fast-diffusers-coreml.md index 6db31c78b8..e20b8a127a 100644 --- a/fast-diffusers-coreml.md +++ b/fast-diffusers-coreml.md @@ -7,8 +7,6 @@ authors: # Faster Stable Diffusion with Core ML on iPhone, iPad, and Mac - - WWDC’23 (Apple Worldwide Developers Conference) was held last week. A lot of the news focused on the Vision Pro announcement during the keynote, but there’s much more to it. Like every year, WWDC week is packed with more than 200 technical sessions that dive deep inside the upcoming features across Apple operating systems and frameworks. This year we are particularly excited about changes in Core ML devoted to compression and optimization techniques. These changes make running [models](https://huggingface.co/apple) such as Stable Diffusion faster and with less memory use! As a taste, consider the following test I ran on my [iPhone 13 back in December](https://huggingface.co/blog/diffusers-coreml), compared with the current speed using 6-bit palettization: diff --git a/fast-mac-diffusers.md b/fast-mac-diffusers.md index 4da7b14b5f..ef174454df 100644 --- a/fast-mac-diffusers.md +++ b/fast-mac-diffusers.md @@ -8,8 +8,6 @@ authors: # Swift 🧨Diffusers: Fast Stable Diffusion for Mac - - Transform your text into stunning images with ease using Diffusers for Mac, a native app powered by state-of-the-art diffusion models. It leverages a bouquet of SoTA Text-to-Image models contributed by the community to the Hugging Face Hub, and converted to Core ML for blazingly fast performance. Our latest version, 1.1, is now available on the [Mac App Store](https://apps.apple.com/app/diffusers/id1666309574) with significant performance upgrades and user-friendly interface tweaks. It's a solid foundation for future feature updates. Plus, the app is fully open source with a permissive [license](https://github.com/huggingface/swift-coreml-diffusers/blob/main/LICENSE), so you can build on it too! Check out our GitHub repository at https://github.com/huggingface/swift-coreml-diffusers for more information. diff --git a/fastai.md b/fastai.md index fa0552d0e5..782febac7a 100644 --- a/fastai.md +++ b/fastai.md @@ -7,8 +7,6 @@ authors: # Welcome fastai to the Hugging Face Hub - - ## Making neural nets uncool again... and sharing them diff --git a/fasttext.md b/fasttext.md index e920142ee6..03e5bd1ccc 100644 --- a/fasttext.md +++ b/fasttext.md @@ -9,8 +9,6 @@ authors: # Welcome fastText to the Hugging Face Hub - - [fastText](https://fasttext.cc/) is a library for efficient learning of text representation and classification. [Open-sourced](https://fasttext.cc/blog/2016/08/18/blog-post.html) by Meta AI in 2016, fastText integrates key ideas that have been influential in natural language processing and machine learning over the past few decades: representing sentences using bag of words and bag of n-grams, using subword information, and utilizing a hidden representation to share information across classes. diff --git a/fellowship.md b/fellowship.md index 3e384c4ad8..e29da6fba5 100644 --- a/fellowship.md +++ b/fellowship.md @@ -8,8 +8,6 @@ authors: # Announcing the Hugging Face Fellowship Program - - 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/fetch-case-study.md b/fetch-case-study.md index 98192f379f..c781f49aff 100644 --- a/fetch-case-study.md +++ b/fetch-case-study.md @@ -5,10 +5,8 @@ authors: - user: VioletteLepercq --- -

Fetch Cuts ML Processing Latency by 50% Using Amazon SageMaker & Hugging Face

+# Fetch Cuts ML Processing Latency by 50% Using Amazon SageMaker & Hugging Face - - _This article is a cross-post from an originally published post on September 2023 [on AWS's website](https://aws.amazon.com/fr/solutions/case-studies/fetch-case-study/)._ diff --git a/few-shot-learning-gpt-neo-and-inference-api.md b/few-shot-learning-gpt-neo-and-inference-api.md index 8d4f18ec80..94b08c0b17 100644 --- a/few-shot-learning-gpt-neo-and-inference-api.md +++ b/few-shot-learning-gpt-neo-and-inference-api.md @@ -7,8 +7,6 @@ authors: # Few-shot learning in practice: GPT-Neo and the 🤗 Accelerated Inference API - - 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 9063f610a4..eb15ab6aa4 100644 --- a/fine-tune-clip-rsicd.md +++ b/fine-tune-clip-rsicd.md @@ -18,8 +18,6 @@ authors: # Fine tuning CLIP with Remote Sensing (Satellite) images and captions - - ## Fine tuning CLIP with Remote Sensing (Satellite) images and captions diff --git a/fine-tune-segformer.md b/fine-tune-segformer.md index eec2abf320..450e4f4241 100644 --- a/fine-tune-segformer.md +++ b/fine-tune-segformer.md @@ -9,8 +9,6 @@ authors: # Fine-Tune a Semantic Segmentation Model with a Custom Dataset - - diff --git a/fine-tune-vit.md b/fine-tune-vit.md index c4fdabd121..54b74eedac 100644 --- a/fine-tune-vit.md +++ b/fine-tune-vit.md @@ -7,8 +7,6 @@ authors: # Fine-Tune ViT for Image Classification with 🤗 Transformers - - diff --git a/fine-tune-wav2vec2-english.md b/fine-tune-wav2vec2-english.md index 664d7eb92d..063579873f 100644 --- a/fine-tune-wav2vec2-english.md +++ b/fine-tune-wav2vec2-english.md @@ -7,8 +7,6 @@ authors: # Fine-Tune Wav2Vec2 for English ASR with 🤗 Transformers - - Open In Colab diff --git a/fine-tune-whisper.md b/fine-tune-whisper.md index fe760c018a..e2dcfd2104 100644 --- a/fine-tune-whisper.md +++ b/fine-tune-whisper.md @@ -7,8 +7,6 @@ authors: # Fine-Tune Whisper For Multilingual ASR with 🤗 Transformers - - Open In Colab diff --git a/fine-tune-xlsr-wav2vec2.md b/fine-tune-xlsr-wav2vec2.md index c4ac6ba3a3..9e5ffc99a7 100644 --- a/fine-tune-xlsr-wav2vec2.md +++ b/fine-tune-xlsr-wav2vec2.md @@ -7,8 +7,6 @@ authors: # Fine-tuning XLS-R for Multi-Lingual ASR with 🤗 Transformers - - Open In Colab diff --git a/fl-with-flower.md b/fl-with-flower.md index c9db95f733..5ff4eb1025 100644 --- a/fl-with-flower.md +++ b/fl-with-flower.md @@ -8,8 +8,6 @@ authors: # Federated Learning using Hugging Face and Flower - - Open In Colab diff --git a/game-jam-first-edition-results.md b/game-jam-first-edition-results.md index f2fae04f6c..2c0170a4a4 100644 --- a/game-jam-first-edition-results.md +++ b/game-jam-first-edition-results.md @@ -12,8 +12,6 @@ authors: # Results of the Open Source AI Game Jam - - From July 7th to July 11th, **we hosted our [first Open Source AI Game Jam](https://itch.io/jam/open-source-ai-game-jam)**, an exciting event that challenged game developers to create innovative games within a tight 48-hour window using AI. diff --git a/game-jam.md b/game-jam.md index 5abf692631..8c66042ab8 100644 --- a/game-jam.md +++ b/game-jam.md @@ -5,10 +5,9 @@ authors: - user: ThomasSimonini --- -

Announcing the Open Source AI Game Jam 🎮

+# Announcing the Open Source AI Game Jam 🎮

Unleash Your Creativity with AI Tools and make a game in a weekend!

- We're thrilled to announce the first ever **Open Source AI Game Jam**, where you will create a game using AI tools. diff --git a/gaussian-splatting.md b/gaussian-splatting.md index d2f127a510..941b2d1340 100644 --- a/gaussian-splatting.md +++ b/gaussian-splatting.md @@ -5,10 +5,8 @@ authors: - user: dylanebert --- -

Introduction to 3D Gaussian Splatting

+# Introduction to 3D Gaussian Splatting - - 3D Gaussian Splatting is a rasterization technique described in [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://huggingface.co/papers/2308.04079) that allows real-time rendering of photorealistic scenes learned from small samples of images. This article will break down how it works and what it means for the future of graphics. diff --git a/generative-ai-models-on-intel-cpu.md b/generative-ai-models-on-intel-cpu.md index 98c1b9f8fc..f8104f4d8c 100644 --- a/generative-ai-models-on-intel-cpu.md +++ b/generative-ai-models-on-intel-cpu.md @@ -9,8 +9,6 @@ authors: - - Large language models (LLMs) are taking the machine learning world by storm. Thanks to their [Transformer](https://arxiv.org/abs/1706.03762) architecture, LLMs have an uncanny ability to learn from vast amounts of unstructured data, like text, images, video, or audio. They perform very well on many [task types](https://huggingface.co/tasks), either extractive like text classification or generative like text summarization and text-to-image generation. diff --git a/getting-started-habana.md b/getting-started-habana.md index 48cc01db4e..8ab1c5776b 100644 --- a/getting-started-habana.md +++ b/getting-started-habana.md @@ -8,8 +8,6 @@ authors: # Getting Started with Transformers on Habana Gaudi - - 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 302aba65cb..79ef3d5782 100644 --- a/getting-started-with-embeddings.md +++ b/getting-started-with-embeddings.md @@ -7,8 +7,6 @@ authors: # Getting Started With Embeddings - - Check out this tutorial with the Notebook Companion: diff --git a/gptj-sagemaker.md b/gptj-sagemaker.md index 47738fda5d..fa763abab6 100644 --- a/gptj-sagemaker.md +++ b/gptj-sagemaker.md @@ -5,10 +5,8 @@ authors: - user: philschmid --- -

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

+# Deploy GPT-J 6B for inference using Hugging Face Transformers and Amazon SageMaker - - diff --git a/gptq-integration.md b/gptq-integration.md index 45c9e00d2a..8878231968 100644 --- a/gptq-integration.md +++ b/gptq-integration.md @@ -15,8 +15,6 @@ authors: # Making LLMs lighter with AutoGPTQ and transformers - - Large language models have demonstrated remarkable capabilities in understanding and generating human-like text, revolutionizing applications across various domains. However, the demands they place on consumer hardware for training and deployment have become increasingly challenging to meet. diff --git a/gradio-blocks.md b/gradio-blocks.md index 0cf99072f0..85e0b2f47c 100644 --- a/gradio-blocks.md +++ b/gradio-blocks.md @@ -5,10 +5,8 @@ authors: - user: abidlabs --- -

Gradio 3.0 is Out!

+# Gradio 3.0 is Out! - - ### Machine Learning Demos diff --git a/gradio-joins-hf.md b/gradio-joins-hf.md index 4da10222ff..9b063655e9 100644 --- a/gradio-joins-hf.md +++ b/gradio-joins-hf.md @@ -5,10 +5,8 @@ authors: - user: abidlabs --- -

Gradio is joining Hugging Face!

+# Gradio is joining Hugging Face! - -

 

diff --git a/gradio-spaces.md b/gradio-spaces.md index a94249db80..73ea7bfed5 100644 --- a/gradio-spaces.md +++ b/gradio-spaces.md @@ -7,8 +7,6 @@ authors: # Showcase Your Projects in Spaces using Gradio - - 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 8d237f86fa..ebd2c5f97c 100644 --- a/gradio.md +++ b/gradio.md @@ -9,8 +9,6 @@ authors: > ##### Cross-posted from the [Gradio blog](https://gradio.app/blog/using-huggingface-models). - - 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 7f9b520b45..07807db943 100644 --- a/graphcore-getting-started.md +++ b/graphcore-getting-started.md @@ -10,7 +10,6 @@ authors: # Getting Started with Hugging Face Transformers for IPUs with Optimum - 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 9756eca02a..47995907fe 100644 --- a/graphcore-update.md +++ b/graphcore-update.md @@ -8,8 +8,6 @@ authors: # Graphcore and Hugging Face Launch New Lineup of IPU-Ready Transformers - - [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 91568992d7..e39a01e0aa 100644 --- a/graphcore.md +++ b/graphcore.md @@ -8,8 +8,6 @@ authors: # Hugging Face and Graphcore partner for IPU-optimized Transformers - - > ##### 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 45d818f14e..e8b249e39b 100644 --- a/habana-gaudi-2-benchmark.md +++ b/habana-gaudi-2-benchmark.md @@ -7,8 +7,6 @@ authors: # Faster Training and Inference: Habana Gaudi®-2 vs Nvidia A100 80GB - - 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-gaudi-2-bloom.md b/habana-gaudi-2-bloom.md index e634a46704..3e56e76046 100644 --- a/habana-gaudi-2-bloom.md +++ b/habana-gaudi-2-bloom.md @@ -7,8 +7,6 @@ authors: # Fast Inference on Large Language Models: BLOOMZ on Habana Gaudi2 Accelerator - - This article will show you how to easily deploy large language models with hundreds of billions of parameters like BLOOM on [Habana® Gaudi®2](https://habana.ai/training/gaudi2/) using 🤗 [Optimum Habana](https://huggingface.co/docs/optimum/habana/index), which is the bridge between Gaudi2 and the 🤗 Transformers library. As demonstrated in the benchmark presented in this post, this will enable you to **run inference faster than with any GPU currently available on the market**. diff --git a/habana.md b/habana.md index e8c9a88e8e..fe61c7d312 100644 --- a/habana.md +++ b/habana.md @@ -8,8 +8,6 @@ authors: # Habana Labs and Hugging Face Partner to Accelerate Transformer Model Training - - *Santa Clara and San Francisco, CA, April 12th, 2022* diff --git a/hardware-partners-program.md b/hardware-partners-program.md index add0e7adda..b983599a8b 100644 --- a/hardware-partners-program.md +++ b/hardware-partners-program.md @@ -10,8 +10,6 @@ authors: # Introducing 🤗 Optimum: The Optimization Toolkit for Transformers at Scale - - 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 58de2a8ee4..7e406aa750 100644 --- a/hf-bitsandbytes-integration.md +++ b/hf-bitsandbytes-integration.md @@ -9,8 +9,6 @@ authors: # A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using Hugging Face Transformers, Accelerate and bitsandbytes - - ![thumbnail](assets/96_hf_bitsandbytes_integration/Thumbnail_blue.png) diff --git a/hf-hub-glam-guide.md b/hf-hub-glam-guide.md index 0e20ed2b74..fb97ff8fdd 100644 --- a/hf-hub-glam-guide.md +++ b/hf-hub-glam-guide.md @@ -8,8 +8,6 @@ authors: ## The Hugging Face Hub for Galleries, Libraries, Archives and Museums - - ### What is the Hugging Face Hub? diff --git a/how-to-deploy-a-pipeline-to-google-clouds.md b/how-to-deploy-a-pipeline-to-google-clouds.md index 977081e52f..c1ef8d2670 100644 --- a/how-to-deploy-a-pipeline-to-google-clouds.md +++ b/how-to-deploy-a-pipeline-to-google-clouds.md @@ -8,8 +8,6 @@ authors: # My Journey to a serverless transformers pipeline on
Google Cloud - - > ##### A guest blog post by community member Maxence Dominici diff --git a/how-to-generate.md b/how-to-generate.md index 0732a5df3d..4157b3313e 100644 --- a/how-to-generate.md +++ b/how-to-generate.md @@ -5,10 +5,8 @@ authors: - user: patrickvonplaten --- -

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

+# How to generate text: using different decoding methods for language generation with Transformers - - Open In Colab diff --git a/how-to-train-sentence-transformers.md b/how-to-train-sentence-transformers.md index 751b371daa..447fe2e392 100644 --- a/how-to-train-sentence-transformers.md +++ b/how-to-train-sentence-transformers.md @@ -7,8 +7,6 @@ authors: # Train and Fine-Tune Sentence Transformers Models - - Check out this tutorial with the Notebook Companion: diff --git a/how-to-train.md b/how-to-train.md index 456115aef8..550bd3a454 100644 --- a/how-to-train.md +++ b/how-to-train.md @@ -5,10 +5,8 @@ authors: - user: julien-c --- -

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

+# How to train a new language model from scratch using Transformers and Tokenizers - - Open In Colab diff --git a/hub-duckdb.md b/hub-duckdb.md index 784e448d65..c8e8306359 100644 --- a/hub-duckdb.md +++ b/hub-duckdb.md @@ -9,8 +9,6 @@ authors: # DuckDB: run SQL queries on 50,000+ datasets on the Hugging Face Hub - - The Hugging Face Hub is dedicated to providing open access to datasets for everyone and giving users the tools to explore and understand them. You can find many of the datasets used to train popular large language models (LLMs) like [Falcon](https://huggingface.co/datasets/tiiuae/falcon-refinedweb), [Dolly](https://huggingface.co/datasets/databricks/databricks-dolly-15k), [MPT](https://huggingface.co/datasets/mosaicml/dolly_hhrlhf), and [StarCoder](https://huggingface.co/datasets/bigcode/the-stack). There are tools for addressing fairness and bias in datasets like [Disaggregators](https://huggingface.co/spaces/society-ethics/disaggregators), and tools for previewing examples inside a dataset like the Dataset Viewer. diff --git a/hugging-face-endpoints-on-azure.md b/hugging-face-endpoints-on-azure.md index e897b594f4..77065b6102 100644 --- a/hugging-face-endpoints-on-azure.md +++ b/hugging-face-endpoints-on-azure.md @@ -9,8 +9,6 @@ authors: # Hugging Face Collaborates with Microsoft to launch Hugging Face Model Catalog on Azure - - ![Hugging Face Endpoints on Azure](assets/75_hugging_face_endpoints_on_azure/01.jpg "Hugging Face Endpoints on Azure") diff --git a/huggingface-and-amd.md b/huggingface-and-amd.md index 835c27b5a8..e8163e26fa 100644 --- a/huggingface-and-amd.md +++ b/huggingface-and-amd.md @@ -8,8 +8,6 @@ authors: # Hugging Face and AMD partner on accelerating state-of-the-art models for CPU and GPU platforms - - diff --git a/huggingface-and-ibm.md b/huggingface-and-ibm.md index 96fb5ae714..576706de65 100644 --- a/huggingface-and-ibm.md +++ b/huggingface-and-ibm.md @@ -8,8 +8,6 @@ authors: # Hugging Face and IBM partner on watsonx.ai, the next-generation enterprise studio for AI builders - - diff --git a/huggy-lingo.md b/huggy-lingo.md index be55451852..4ae9c00191 100644 --- a/huggy-lingo.md +++ b/huggy-lingo.md @@ -8,8 +8,6 @@ authors: ## Huggy Lingo: Using Machine Learning to Improve Language Metadata on the Hugging Face Hub - - **tl;dr**: We're using machine learning to detect the language of Hub datasets with no language metadata, and [librarian-bots](https://huggingface.co/librarian-bots) to make pull requests to add this metadata. diff --git a/huggylingo.md b/huggylingo.md index 50b91c2980..25001f4a54 100644 --- a/huggylingo.md +++ b/huggylingo.md @@ -8,8 +8,6 @@ authors: ## Huggy Lingo: Using Machine Learning to Improve Language Metadata on the Hugging Face Hub - - **tl;dr**: We're using machine learning to detect the language of Hub datasets with no language metadata, and [librarian-bots](https://huggingface.co/librarian-bots) to make pull requests to add this metadata. diff --git a/idefics.md b/idefics.md index 0c84cc49c4..e01c481621 100644 --- a/idefics.md +++ b/idefics.md @@ -20,8 +20,6 @@ authors: # Introducing IDEFICS: An Open Reproduction of State-of-the-Art Visual Language Model - - We are excited to release IDEFICS (**I**mage-aware **D**ecoder **E**nhanced à la **F**lamingo with **I**nterleaved **C**ross-attention**S**), an open-access visual language model. IDEFICS is based on [Flamingo](https://huggingface.co/papers/2204.14198), a state-of-the-art visual language model initially developed by DeepMind, which has not been released publicly. Similarly to GPT-4, the model accepts arbitrary sequences of image and text inputs and produces text outputs. IDEFICS is built solely on publicly available data and models (LLaMA v1 and OpenCLIP) and comes in two variants—the base version and the instructed version. Each variant is available at the 9 billion and 80 billion parameter sizes. diff --git a/if.md b/if.md index 9a294fecdf..63777790c9 100644 --- a/if.md +++ b/if.md @@ -19,8 +19,6 @@ authors: Open In Colab - - **TL;DR**: We show how to run one of the most powerful open-source text to image models **IF** on a free-tier Google Colab with 🧨 diffusers. diff --git a/image-search-datasets.md b/image-search-datasets.md index 13c7009466..2db857922c 100644 --- a/image-search-datasets.md +++ b/image-search-datasets.md @@ -6,10 +6,8 @@ authors: guest: true --- -

Image search with 🤗 datasets

+# Image search with 🤗 datasets - - Open In Colab diff --git a/image-similarity.md b/image-similarity.md index 46cefadb0e..3daf21749e 100644 --- a/image-similarity.md +++ b/image-similarity.md @@ -7,8 +7,6 @@ authors: # Image Similarity with Hugging Face Datasets and Transformers - - Open In Colab diff --git a/inference-endpoints-llm.md b/inference-endpoints-llm.md index 4dd95766cb..2553dff554 100644 --- a/inference-endpoints-llm.md +++ b/inference-endpoints-llm.md @@ -7,8 +7,6 @@ authors: # Deploy LLMs with Hugging Face Inference Endpoints - - Open-source LLMs like [Falcon](https://huggingface.co/tiiuae/falcon-40b), [(Open-)LLaMA](https://huggingface.co/openlm-research/open_llama_13b), [X-Gen](https://huggingface.co/Salesforce/xgen-7b-8k-base), [StarCoder](https://huggingface.co/bigcode/starcoder) or [RedPajama](https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Base), have come a long way in recent months and can compete with closed-source models like ChatGPT or GPT4 for certain use cases. However, deploying these models in an efficient and optimized way still presents a challenge. diff --git a/inference-endpoints.md b/inference-endpoints.md index 8771cff81b..a1b2258d5b 100644 --- a/inference-endpoints.md +++ b/inference-endpoints.md @@ -7,8 +7,6 @@ authors: # Getting Started with Hugging Face Inference Endpoints - - 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-pro.md b/inference-pro.md index 79e4562c60..1b72451d69 100644 --- a/inference-pro.md +++ b/inference-pro.md @@ -9,8 +9,6 @@ authors: # Inference for PROs - - ![Inference for PROs image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/inference-for-pros/Inference-for-pros.png) diff --git a/inference-update.md b/inference-update.md index ad63ed447d..4d631c2df7 100644 --- a/inference-update.md +++ b/inference-update.md @@ -5,10 +5,8 @@ authors: - user: juliensimon --- -

An Overview of Inference Solutions on Hugging Face

+# An Overview of Inference Solutions on Hugging Face - - 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 7aa1e6ba33..25d3a52a68 100644 --- a/infinity-cpu-performance.md +++ b/infinity-cpu-performance.md @@ -6,10 +6,8 @@ authors: - user: jeffboudier - user: mfuntowicz --- -

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

+# Case Study: Millisecond Latency using Hugging Face Infinity and modern CPUs - - diff --git a/informer.md b/informer.md index c334b2164b..08f4379789 100644 --- a/informer.md +++ b/informer.md @@ -10,8 +10,6 @@ authors: # Multivariate Probabilistic Time Series Forecasting with Informer - - diff --git a/instruction-tuning-sd.md b/instruction-tuning-sd.md index a37ccdac51..e9563186b7 100644 --- a/instruction-tuning-sd.md +++ b/instruction-tuning-sd.md @@ -7,8 +7,6 @@ authors: # Instruction-tuning Stable Diffusion with InstructPix2Pix - - This post explores instruction-tuning to teach [Stable Diffusion](https://huggingface.co/blog/stable_diffusion) to follow instructions to translate or process input images. With this method, we can prompt Stable Diffusion using an input image and an “instruction”, such as - *Apply a cartoon filter to the natural image*. diff --git a/intel-sapphire-rapids-inference.md b/intel-sapphire-rapids-inference.md index ace80170b4..188cf669df 100644 --- a/intel-sapphire-rapids-inference.md +++ b/intel-sapphire-rapids-inference.md @@ -7,8 +7,6 @@ authors: # Accelerating PyTorch Transformers with Intel Sapphire Rapids, part 2 - - In a [recent post](https://huggingface.co/blog/intel-sapphire-rapids), we introduced you to the fourth generation of Intel Xeon CPUs, code-named [Sapphire Rapids](https://en.wikipedia.org/wiki/Sapphire_Rapids), and its new Advanced Matrix Extensions ([AMX](https://en.wikipedia.org/wiki/Advanced_Matrix_Extensions)) instruction set. Combining a cluster of Sapphire Rapids servers running on Amazon EC2 and Intel libraries like the [Intel Extension for PyTorch](https://github.com/intel/intel-extension-for-pytorch), we showed you how to efficiently run distributed training at scale, achieving an 8-fold speedup compared to the previous Xeon generation (Ice Lake) with near-linear scaling. diff --git a/intel-sapphire-rapids.md b/intel-sapphire-rapids.md index 5a9724b7d4..ee6b407491 100644 --- a/intel-sapphire-rapids.md +++ b/intel-sapphire-rapids.md @@ -5,12 +5,7 @@ authors: - user: juliensimon --- -

-Accelerating PyTorch Transformers with Intel Sapphire Rapids, part 1

- - - - +# Accelerating PyTorch Transformers with Intel Sapphire Rapids, part 1 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 b798a7261f..415045beff 100644 --- a/intel.md +++ b/intel.md @@ -7,12 +7,10 @@ authors: -

Intel and Hugging Face Partner to Democratize Machine Learning Hardware Acceleration

+# Intel and Hugging Face Partner to Democratize Machine Learning Hardware Acceleration - - ![image](assets/80_intel/01.png) diff --git a/interns-2023.md b/interns-2023.md index ab7318e168..e0f68ed988 100644 --- a/interns-2023.md +++ b/interns-2023.md @@ -8,8 +8,6 @@ authors: # We are hiring interns! - - 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 0c98a4bb1b..d6f93db84a 100644 --- a/intro-graphml.md +++ b/intro-graphml.md @@ -7,8 +7,6 @@ authors: # Introduction to Graph Machine Learning - - In this blog post, we cover the basics of graph machine learning. diff --git a/introducing-csearch.md b/introducing-csearch.md index 9ca64630e0..a3cd1c40e4 100644 --- a/introducing-csearch.md +++ b/introducing-csearch.md @@ -5,10 +5,8 @@ authors: - user: GMFTBY --- -

Generating Human-level Text with Contrastive Search in Transformers 🤗

+# Generating Human-level Text with Contrastive Search in Transformers 🤗 - - **** diff --git a/introducing-doi.md b/introducing-doi.md index fdc26ad7d0..042d2b4ce6 100644 --- a/introducing-doi.md +++ b/introducing-doi.md @@ -14,8 +14,6 @@ authors: # Introducing DOI: the Digital Object Identifier to Datasets and Models - - 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 de93fd638c..60a8e81a82 100644 --- a/introducing-private-hub.md +++ b/introducing-private-hub.md @@ -5,10 +5,8 @@ authors: - user: federicopascual --- -

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

+# Introducing the Private Hub: A New Way to Build With Machine Learning - - diff --git a/japanese-stable-diffusion.md b/japanese-stable-diffusion.md index ce0465c81a..cd13206e8d 100644 --- a/japanese-stable-diffusion.md +++ b/japanese-stable-diffusion.md @@ -10,8 +10,6 @@ authors: # Japanese Stable Diffusion - - Open In Hugging Face Spaces diff --git a/large-language-models.md b/large-language-models.md index e07da8c200..abf03ca3c4 100644 --- a/large-language-models.md +++ b/large-language-models.md @@ -8,8 +8,6 @@ authors: # Large Language Models: A New Moore's Law? - - 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 5b785ef584..7232dc1873 100644 --- a/lewis-tunstall-interview.md +++ b/lewis-tunstall-interview.md @@ -5,10 +5,8 @@ authors: - user: britneymuller --- -

Machine Learning Experts - Lewis Tunstall

+# Machine Learning Experts - Lewis Tunstall - - ## 🤗 Welcome to Machine Learning Experts - Lewis Tunstall diff --git a/livebook-app-deployment.md b/livebook-app-deployment.md index e9ecf7be59..02a255f536 100644 --- a/livebook-app-deployment.md +++ b/livebook-app-deployment.md @@ -8,8 +8,6 @@ authors: # Deploy Livebook notebooks as apps to Hugging Face Spaces - - The [Elixir](https://elixir-lang.org/) community has been making great strides towards Machine Learning and Hugging Face is playing an important role on making it possible. To showcase what you can already achieve with Elixir and Machine Learning today, we use [Livebook](https://livebook.dev/) to build a Whisper-based chat app and then deploy it to Hugging Face Spaces. All under 15 minutes, check it out: diff --git a/llama-sagemaker-benchmark.md b/llama-sagemaker-benchmark.md index 5371a9b68e..0d974a073d 100644 --- a/llama-sagemaker-benchmark.md +++ b/llama-sagemaker-benchmark.md @@ -7,8 +7,6 @@ authors: # Llama 2 on Amazon SageMaker a Benchmark - - ![Latency](assets/llama_sagemaker_benchmark/latency.png "Latency") diff --git a/llama2.md b/llama2.md index 5ae1886759..65ccfa7b41 100644 --- a/llama2.md +++ b/llama2.md @@ -10,8 +10,6 @@ authors: # Llama 2 is here - get it on Hugging Face - - ## Introduction diff --git a/llm-leaderboard.md b/llm-leaderboard.md index 98efcc8dc4..3c40d4c280 100644 --- a/llm-leaderboard.md +++ b/llm-leaderboard.md @@ -17,8 +17,6 @@ authors: --- # Can foundation models label data like humans? - - Since the advent of ChatGPT, we have seen unprecedented growth in the development of Large Language Models (LLMs), and particularly chatty models that are fine-tuned to follow instructions given in the form of prompts. However, how these models compare is unclear due to the lack of benchmarks designed to test their performance rigorously. diff --git a/long-range-transformers.md b/long-range-transformers.md index 6259d66574..616a83116a 100644 --- a/long-range-transformers.md +++ b/long-range-transformers.md @@ -12,8 +12,6 @@ authors: # Hugging Face Reads, Feb. 2021 - Long-range Transformers - - 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 0e4b22c060..382c226ba8 100644 --- a/lora.md +++ b/lora.md @@ -8,8 +8,6 @@ authors: # Using LoRA for Efficient Stable Diffusion Fine-Tuning - - [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/mantis-case-study.md b/mantis-case-study.md index ddce688b7f..a3eb97960e 100644 --- a/mantis-case-study.md +++ b/mantis-case-study.md @@ -6,11 +6,9 @@ authors: guest: true --- -

Why we’re switching to Hugging Face Inference Endpoints, and maybe you should too

+# Why we’re switching to Hugging Face Inference Endpoints, and maybe you should too - - Hugging Face recently launched [Inference Endpoints](https://huggingface.co/inference-endpoints); which as they put it: solves transformers in production. Inference Endpoints is a managed service that allows you to: diff --git a/mask2former.md b/mask2former.md index ca8e93224a..9043aba30f 100644 --- a/mask2former.md +++ b/mask2former.md @@ -9,8 +9,6 @@ authors: # Universal Image Segmentation with Mask2Former and OneFormer - - diff --git a/meg-mitchell-interview.md b/meg-mitchell-interview.md index 710a7a9422..2e2ea1174f 100644 --- a/meg-mitchell-interview.md +++ b/meg-mitchell-interview.md @@ -5,10 +5,8 @@ authors: - user: britneymuller --- -

Machine Learning Experts - Margaret Mitchell

+# Machine Learning Experts - Margaret Mitchell - - 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 c8fd0774c9..92604d0d43 100644 --- a/megatron-training.md +++ b/megatron-training.md @@ -5,10 +5,8 @@ authors: - user: loubnabnl --- -

How to train a Language Model with Megatron-LM

+# How to train a Language Model with Megatron-LM - - 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 d2d5160478..f0d59f50ad 100644 --- a/ml-director-insights-2.md +++ b/ml-director-insights-2.md @@ -5,10 +5,8 @@ authors: - user: britneymuller --- -

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

+# Director of Machine Learning Insights [Part 2: SaaS Edition] - - _If you or your team are interested in building ML solutions faster visit [hf.co/support](https://huggingface.co/support?utm_source=article&utm_medium=blog&utm_campaign=ml_director_insights_2) today!_ diff --git a/ml-director-insights-3.md b/ml-director-insights-3.md index 2c04774599..3047b3aee8 100644 --- a/ml-director-insights-3.md +++ b/ml-director-insights-3.md @@ -5,10 +5,8 @@ authors: - user: britneymuller --- -

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

+# Director of Machine Learning Insights [Part 3: Finance Edition] - - _If you're interested in building ML solutions faster visit [hf.co/support](https://huggingface.co/support?utm_source=article&utm_medium=blog&utm_campaign=ml_director_insights_3) today!_ diff --git a/ml-director-insights-4.md b/ml-director-insights-4.md index 7f849f2569..18fa3adb02 100644 --- a/ml-director-insights-4.md +++ b/ml-director-insights-4.md @@ -4,9 +4,8 @@ thumbnail: /blog/assets/78_ml_director_insights/part4.png --- -

Director of Machine Learning Insights [Part 4]

+# Director of Machine Learning Insights [Part 4] - _If you're interested in building ML solutions faster visit: [hf.co/support](https://huggingface.co/support?utm_source=article&utm_medium=blog&utm_campaign=ml_director_insights_3) today!_ diff --git a/ml-director-insights.md b/ml-director-insights.md index 3d5b55e206..a95f7475ec 100644 --- a/ml-director-insights.md +++ b/ml-director-insights.md @@ -5,10 +5,8 @@ authors: - user: britneymuller --- -

Director of Machine Learning Insights [Part 1]

+# Director of Machine Learning Insights [Part 1] - - Few seats at the Machine Learning table span both technical skills, problem solving and business acumen like Directors of Machine Learning diff --git a/ml-for-games-1.md b/ml-for-games-1.md index e55561a409..fbc9aa1517 100644 --- a/ml-for-games-1.md +++ b/ml-for-games-1.md @@ -5,9 +5,8 @@ authors: - user: dylanebert --- -

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

+# AI for Game Development: Creating a Farming Game in 5 Days. Part 1 - diff --git a/ml-for-games-2.md b/ml-for-games-2.md index 86e265ce40..6c00861c5d 100644 --- a/ml-for-games-2.md +++ b/ml-for-games-2.md @@ -5,10 +5,8 @@ authors: - user: dylanebert --- -

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

+# AI for Game Development: Creating a Farming Game in 5 Days. Part 2 - - **Welcome to AI for Game Development!** In this series, we'll be using AI tools to create a fully functional farming game in just 5 days. By the end of this series, you will have learned how you can incorporate a variety of AI tools into your game development workflow. I will show you how you can use AI tools for: diff --git a/ml-for-games-3.md b/ml-for-games-3.md index 51edd51f18..164bb82cfc 100644 --- a/ml-for-games-3.md +++ b/ml-for-games-3.md @@ -5,10 +5,8 @@ authors: - user: dylanebert --- -

3D Asset Generation: AI for Game Development #3

+# 3D Asset Generation: AI for Game Development #3 - - **Welcome to AI for Game Development!** In this series, we'll be using AI tools to create a fully functional farming game in just 5 days. By the end of this series, you will have learned how you can incorporate a variety of AI tools into your game development workflow. I will show you how you can use AI tools for: diff --git a/ml-for-games-4.md b/ml-for-games-4.md index 31ba710964..2c96b2ca79 100644 --- a/ml-for-games-4.md +++ b/ml-for-games-4.md @@ -5,10 +5,8 @@ authors: - user: dylanebert --- -

2D Asset Generation: AI for Game Development #4

+# 2D Asset Generation: AI for Game Development #4 - - **Welcome to AI for Game Development!** In this series, we'll be using AI tools to create a fully functional farming game in just 5 days. By the end of this series, you will have learned how you can incorporate a variety of AI tools into your game development workflow. I will show you how you can use AI tools for: diff --git a/ml-for-games-5.md b/ml-for-games-5.md index 3bdab4a8fe..560f10c4b1 100644 --- a/ml-for-games-5.md +++ b/ml-for-games-5.md @@ -5,10 +5,8 @@ authors: - user: dylanebert --- -

Generating Stories: AI for Game Development #5

+# Generating Stories: AI for Game Development #5 - - **Welcome to AI for Game Development!** In this series, we'll be using AI tools to create a fully functional farming game in just 5 days. By the end of this series, you will have learned how you can incorporate a variety of AI tools into your game development workflow. I will show you how you can use AI tools for: diff --git a/ml-web-games.md b/ml-web-games.md index c056bf1743..19505d44c6 100644 --- a/ml-web-games.md +++ b/ml-web-games.md @@ -8,8 +8,6 @@ authors: # Making ML-powered web games with Transformers.js - - In this blog post, I'll show you how I made [**Doodle Dash**](https://huggingface.co/spaces/Xenova/doodle-dash), a real-time ML-powered web game that runs completely in your browser (thanks to [Transformers.js](https://github.com/xenova/transformers.js)). The goal of this tutorial is to show you how easy it is to make your own ML-powered web game... just in time for the upcoming Open Source AI Game Jam (7-9 July 2023). [Join](https://itch.io/jam/open-source-ai-game-jam) the game jam if you haven't already! diff --git a/mms_adapters.md b/mms_adapters.md index 4dbabe1e6d..065f34b5b6 100644 --- a/mms_adapters.md +++ b/mms_adapters.md @@ -7,8 +7,6 @@ authors: # **Fine-tuning MMS Adapter Models for Multi-Lingual ASR** - - Open In Colab diff --git a/mnist-adversarial.md b/mnist-adversarial.md index cb82698d2e..4f3d059a8a 100644 --- a/mnist-adversarial.md +++ b/mnist-adversarial.md @@ -7,8 +7,6 @@ authors: # How to train your model dynamically using adversarial data - - ##### 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 ed71036c2b..4b0bf4cc9d 100644 --- a/model-cards.md +++ b/model-cards.md @@ -9,8 +9,6 @@ authors: # Model Cards - - ## 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 870fe66c22..582a01534a 100644 --- a/mteb.md +++ b/mteb.md @@ -6,10 +6,8 @@ authors: --- -

MTEB: Massive Text Embedding Benchmark

+# MTEB: Massive Text Embedding Benchmark - - MTEB is a massive benchmark for measuring the performance of text embedding models on diverse embedding tasks. diff --git a/notebooks-hub.md b/notebooks-hub.md index bfd78c7264..f028f607b3 100644 --- a/notebooks-hub.md +++ b/notebooks-hub.md @@ -7,10 +7,8 @@ authors: - user: merve --- -

Jupyter X Hugging Face

+# Jupyter X Hugging Face - - **We’re excited to announce improved support for Jupyter notebooks hosted on the Hugging Face Hub!** diff --git a/nystromformer.md b/nystromformer.md index 04f092a438..c233dac361 100644 --- a/nystromformer.md +++ b/nystromformer.md @@ -6,10 +6,8 @@ authors: guest: true --- -

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

+# Nyströmformer: Approximating self-attention in linear time and memory via the Nyström method - - diff --git a/object-detection-leaderboard.md b/object-detection-leaderboard.md index 23f54a1023..047ecfa682 100644 --- a/object-detection-leaderboard.md +++ b/object-detection-leaderboard.md @@ -7,8 +7,6 @@ authors: --- - - # Object Detection Leaderboard: Decoding Metrics and Their Potential Pitfalls diff --git a/open_rail.md b/open_rail.md index eb29775aee..f9bf3e4572 100644 --- a/open_rail.md +++ b/open_rail.md @@ -6,10 +6,8 @@ authors: --- -

OpenRAIL: Towards open and responsible AI licensing frameworks

+# OpenRAIL: Towards open and responsible AI licensing frameworks - - 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 edacb0fa7f..6ebb04c6d0 100644 --- a/openvino.md +++ b/openvino.md @@ -6,10 +6,8 @@ authors: - user: juliensimon --- -

Accelerate your models with 🤗 Optimum Intel and OpenVINO

+# Accelerate your models with 🤗 Optimum Intel and OpenVINO - - ![image](assets/113_openvino/thumbnail.png) diff --git a/opinion-classification-with-kili.md b/opinion-classification-with-kili.md index 8af7cde492..f9016c8ac1 100644 --- a/opinion-classification-with-kili.md +++ b/opinion-classification-with-kili.md @@ -8,8 +8,6 @@ authors: # Opinion Classification with Kili and HuggingFace AutoTrain - - ## Introduction diff --git a/optimize-llm.md b/optimize-llm.md index e244c210cc..2ce09941ac 100644 --- a/optimize-llm.md +++ b/optimize-llm.md @@ -7,8 +7,6 @@ authors: # Optimizing your LLM in production - - Open In Colab diff --git a/optimizing-bark.md b/optimizing-bark.md index 1cd0e15180..ff76ce20d9 100644 --- a/optimizing-bark.md +++ b/optimizing-bark.md @@ -7,8 +7,6 @@ authors: # Optimizing a Text-To-Speech model using 🤗 Transformers - - diff --git a/optimum-inference.md b/optimum-inference.md index 2ed8e88905..1a8c4dc1aa 100644 --- a/optimum-inference.md +++ b/optimum-inference.md @@ -7,8 +7,6 @@ authors: # Accelerated Inference with Optimum and Transformers Pipelines - - > 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 902e64fbcd..0155e088cb 100644 --- a/optimum-onnxruntime-training.md +++ b/optimum-onnxruntime-training.md @@ -15,8 +15,6 @@ authors: # Optimum + ONNX Runtime: Easier, Faster training for your Hugging Face models - - ## Introduction diff --git a/os-llms.md b/os-llms.md index 9135e092b9..fd354c5798 100644 --- a/os-llms.md +++ b/os-llms.md @@ -5,10 +5,8 @@ authors: - user: merve --- -

Open-Source Text Generation & LLM Ecosystem at Hugging Face

+# Open-Source Text Generation & LLM Ecosystem at Hugging Face - - [Updated on July 24, 2023: Added Llama 2.] diff --git a/overview-quantization-transformers.md b/overview-quantization-transformers.md index bc8e657a4c..15b62e81f0 100644 --- a/overview-quantization-transformers.md +++ b/overview-quantization-transformers.md @@ -11,8 +11,6 @@ authors: # Overview of natively supported quantization schemes in 🤗 Transformers - - We aim to give a clear overview of the pros and cons of each quantization scheme supported in transformers to help you decide which one you should go for. diff --git a/owkin-substra.md b/owkin-substra.md index b3fba720c6..30bfd891e8 100644 --- a/owkin-substra.md +++ b/owkin-substra.md @@ -11,8 +11,6 @@ authors: # Creating Privacy Preserving AI with Substra - - With the recent rise of generative techniques, machine learning is at an incredibly exciting point in its history. The models powering this rise require even more data to produce impactful results, and thus it’s becoming increasingly important to explore new methods of ethically gathering data while ensuring that data privacy and security remain a top priority. diff --git a/paddlepaddle.md b/paddlepaddle.md index 6ca6ca63e2..3188711970 100644 --- a/paddlepaddle.md +++ b/paddlepaddle.md @@ -8,8 +8,6 @@ authors: # Welcome PaddlePaddle to the Hugging Face Hub - - 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/panel-on-hugging-face.md b/panel-on-hugging-face.md index 95f3454f99..5c9d9091c0 100644 --- a/panel-on-hugging-face.md +++ b/panel-on-hugging-face.md @@ -10,8 +10,6 @@ authors: # Panel on Hugging Face - - We are thrilled to announce the collaboration between Panel and Hugging Face! 🎉 We have integrated a Panel template in Hugging Face Spaces to help you get started building Panel apps and deploy them on Hugging Face effortlessly. diff --git a/password-git-deprecation.md b/password-git-deprecation.md index d15f497fe5..60355e5445 100644 --- a/password-git-deprecation.md +++ b/password-git-deprecation.md @@ -10,8 +10,6 @@ authors: # Hugging Face Hub: Important Git Authentication Changes - - Because we are committed to improving the security of our services, we are making changes to the way you authenticate when interacting with the Hugging Face Hub through Git. Starting from **October 1st, 2023**, we will no longer accept passwords as a way to authenticate your command-line Git operations. Instead, we recommend using more secure authentication methods, such as replacing the password with a personal access token or using an SSH key. diff --git a/peft.md b/peft.md index c633ddc584..8f9c85417a 100644 --- a/peft.md +++ b/peft.md @@ -6,10 +6,8 @@ authors: - user: sayakpaul --- -

🤗 PEFT: Parameter-Efficient Fine-Tuning of Billion-Scale Models on Low-Resource Hardware

+# 🤗 PEFT: Parameter-Efficient Fine-Tuning of Billion-Scale Models on Low-Resource Hardware - - ## Motivation diff --git a/perceiver.md b/perceiver.md index 8f157a9878..e2689e0de8 100644 --- a/perceiver.md +++ b/perceiver.md @@ -5,10 +5,8 @@ authors: - user: nielsr --- -

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

+# Perceiver IO: a scalable, fully-attentional model that works on any modality - - ### TLDR diff --git a/playlist-generator.md b/playlist-generator.md index 8761ea277f..c0a3540c7f 100644 --- a/playlist-generator.md +++ b/playlist-generator.md @@ -7,8 +7,6 @@ authors: # Building a Playlist Generator with Sentence Transformers - - diff --git a/policy-ntia-rfc.md b/policy-ntia-rfc.md index 4f4210b4ab..1a522224b0 100644 --- a/policy-ntia-rfc.md +++ b/policy-ntia-rfc.md @@ -7,7 +7,7 @@ authors: - user: irenesolaiman --- -

AI Policy @🤗: Response to the U.S. National Telecommunications and Information Administration’s (NTIA) Request for Comment on AI Accountability

+# AI Policy @🤗: Response to the U.S. National Telecommunications and Information Administration’s (NTIA) Request for Comment on AI Accountability On June 12th, Hugging Face submitted a response to the US Department of Commerce NTIA request for information on AI Accountability policy. In our response, we stressed the role of documentation and transparency norms in driving AI accountability processes, as well as the necessity of relying on the full range of expertise, perspectives, and skills of the technology’s many stakeholders to address the daunting prospects of a technology whose unprecedented growth poses more questions than any single entity can answer. @@ -21,5 +21,3 @@ Concretely, we make the following recommendations for accountability mechanisms: We believe that prioritizing transparency in both the ML artifacts themselves and the outcomes of their assessment will be integral to meeting these goals. You can find our more detailed response addressing these points here. - - diff --git a/porting-fsmt.md b/porting-fsmt.md index 0378df5ee5..e8c5c74884 100644 --- a/porting-fsmt.md +++ b/porting-fsmt.md @@ -6,10 +6,8 @@ authors: guest: true --- -

Porting fairseq wmt19 translation system to transformers

+# Porting fairseq wmt19 translation system to transformers - - ##### A guest blog post by Stas Bekman diff --git a/pretraining-bert.md b/pretraining-bert.md index 2efdcf752e..b0736cbf98 100644 --- a/pretraining-bert.md +++ b/pretraining-bert.md @@ -7,8 +7,6 @@ authors: # Pre-Training BERT with Hugging Face Transformers and Habana Gaudi - - 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 c8b67203cd..7104b2c797 100644 --- a/pricing-update.md +++ b/pricing-update.md @@ -6,10 +6,8 @@ authors: - user: pierric --- -

Introducing our new pricing

+# Introducing our new pricing - - 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 8815b7f5f2..c197dbead8 100644 --- a/pytorch-ddp-accelerate-transformers.md +++ b/pytorch-ddp-accelerate-transformers.md @@ -7,8 +7,6 @@ authors: # From PyTorch DDP to Accelerate to Trainer, mastery of distributed training with ease - - ## General Overview diff --git a/pytorch-fsdp.md b/pytorch-fsdp.md index 870c43a162..ea275a3a32 100644 --- a/pytorch-fsdp.md +++ b/pytorch-fsdp.md @@ -6,10 +6,8 @@ authors: - user: sgugger --- -

Accelerate Large Model Training using PyTorch Fully Sharded Data Parallel

+# Accelerate Large Model Training using PyTorch Fully Sharded Data Parallel - - 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 da1311fcd3..d4419e3b04 100644 --- a/pytorch-xla.md +++ b/pytorch-xla.md @@ -7,10 +7,8 @@ authors: - user: lysandre --- -

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

+# Hugging Face on PyTorch / XLA TPUs: Faster and cheaper training - - Open In Colab diff --git a/pytorch_block_sparse.md b/pytorch_block_sparse.md index 02a654baed..dbb38226ff 100644 --- a/pytorch_block_sparse.md +++ b/pytorch_block_sparse.md @@ -5,10 +5,8 @@ authors: - user: madlag --- -

Block Sparse Matrices for Smaller and Faster Language Models

+# Block Sparse Matrices for Smaller and Faster Language Models - - ## Saving space and time, one zero at a time diff --git a/ram-efficient-pytorch-fsdp.md b/ram-efficient-pytorch-fsdp.md index 86d2dbb9ce..3b9b36a4da 100644 --- a/ram-efficient-pytorch-fsdp.md +++ b/ram-efficient-pytorch-fsdp.md @@ -9,8 +9,6 @@ authors: --- # Fine-tuning Llama 2 70B using PyTorch FSDP - - ## Introduction diff --git a/ray-rag.md b/ray-rag.md index adc878b91e..d533105b26 100644 --- a/ray-rag.md +++ b/ray-rag.md @@ -8,8 +8,6 @@ authors: # Retrieval Augmented Generation with Huggingface Transformers and Ray - - ##### A guest blog post by Amog Kamsetty from the Anyscale team diff --git a/ray-tune.md b/ray-tune.md index 338bcc67e6..d77ea36362 100644 --- a/ray-tune.md +++ b/ray-tune.md @@ -8,8 +8,6 @@ authors: # Hyperparameter Search with Transformers and Ray Tune - - ##### A guest blog post by Richard Liaw from the Anyscale team diff --git a/red-teaming.md b/red-teaming.md index f272e817fe..8f71cc86a1 100644 --- a/red-teaming.md +++ b/red-teaming.md @@ -9,8 +9,6 @@ authors: # Red-Teaming Large Language Models - - *Warning: This article is about red-teaming and as such contains examples of model generation that may be offensive or upsetting.* diff --git a/reformer.md b/reformer.md index 00e5cd2a7d..07584251dc 100644 --- a/reformer.md +++ b/reformer.md @@ -5,10 +5,8 @@ authors: - user: patrickvonplaten --- -

The Reformer - Pushing the limits of language modeling

+# The Reformer - Pushing the limits of language modeling - - Open In Colab diff --git a/rlhf.md b/rlhf.md index 0521664ec4..00fcf76148 100644 --- a/rlhf.md +++ b/rlhf.md @@ -12,8 +12,6 @@ authors: # Illustrating Reinforcement Learning from Human Feedback (RLHF) - - _This article has been translated to Chinese [简体中文](https://huggingface.co/blog/zh/rlhf) and Vietnamese [đọc tiếng việt](https://trituenhantao.io/kien-thuc/minh-hoa-rlhf-vu-khi-dang-sau-gpt/)_. diff --git a/rocketmoney-case-study.md b/rocketmoney-case-study.md index 0423ef443d..fa4d20f24e 100644 --- a/rocketmoney-case-study.md +++ b/rocketmoney-case-study.md @@ -8,10 +8,8 @@ authors: guest: true --- -

Rocket Money x Hugging Face: Scaling Volatile ML Models in Production

+# Rocket Money x Hugging Face: Scaling Volatile ML Models in Production - - #### "We discovered that they were not just service providers, but partners who were invested in our goals and outcomes” _- Nicolas Kuzak, Senior ML Engineer at Rocket Money._ diff --git a/run-musicgen-as-an-api.md b/run-musicgen-as-an-api.md index ce02985e6c..46897ef563 100644 --- a/run-musicgen-as-an-api.md +++ b/run-musicgen-as-an-api.md @@ -6,10 +6,8 @@ authors: - user: merve --- -

Deploy MusicGen in no time with Inference Endpoints

+# Deploy MusicGen in no time with Inference Endpoints - - [MusicGen](https://huggingface.co/docs/transformers/main/en/model_doc/musicgen) is a powerful music generation model that takes in text prompt and an optional melody to output music. This blog post will guide you through generating music with MusicGen using [Inference Endpoints](https://huggingface.co/inference-endpoints). diff --git a/rwkv.md b/rwkv.md index 2a343a79b4..a2da729df3 100644 --- a/rwkv.md +++ b/rwkv.md @@ -12,8 +12,6 @@ authors: # Introducing RWKV - An RNN with the advantages of a transformer - - ChatGPT and chatbot-powered applications have captured significant attention in the Natural Language Processing (NLP) domain. The community is constantly seeking strong, reliable and open-source models for their applications and use cases. The rise of these powerful models stems from the democratization and widespread adoption of transformer-based models, first introduced by Vaswani et al. in 2017. These models significantly outperformed previous SoTA NLP models based on Recurrent Neural Networks (RNNs), which were considered dead after that paper. diff --git a/safecoder-vs-closed-source-code-assistants.md b/safecoder-vs-closed-source-code-assistants.md index ed23b16fe6..83da3cbb6a 100644 --- a/safecoder-vs-closed-source-code-assistants.md +++ b/safecoder-vs-closed-source-code-assistants.md @@ -7,8 +7,6 @@ authors: # SafeCoder vs. Closed-source Code Assistants - - For decades, software developers have designed methodologies, processes, and tools that help them improve code quality and increase productivity. For instance, agile, test-driven development, code reviews, and CI/CD are now staples in the software industry. diff --git a/safecoder.md b/safecoder.md index 2338e49c45..527d01607f 100644 --- a/safecoder.md +++ b/safecoder.md @@ -8,8 +8,6 @@ authors: # Introducing SafeCoder - - Today we are excited to announce SafeCoder - a code assistant solution built for the enterprise. diff --git a/safetensors-security-audit.md b/safetensors-security-audit.md index 0096184013..cadd675d27 100644 --- a/safetensors-security-audit.md +++ b/safetensors-security-audit.md @@ -9,8 +9,6 @@ authors: # Audit shows that safetensors is safe and ready to become the default - - [Hugging Face](https://huggingface.co/), in close collaboration with [EleutherAI](https://www.eleuther.ai/) and [Stability AI](https://stability.ai/), has ordered an external security audit of the `safetensors` library, the results of which allow diff --git a/sagemaker-distributed-training-seq2seq.md b/sagemaker-distributed-training-seq2seq.md index 6809d2ea92..65d6bb60ef 100644 --- a/sagemaker-distributed-training-seq2seq.md +++ b/sagemaker-distributed-training-seq2seq.md @@ -7,8 +7,6 @@ authors: # Distributed Training: Train BART/T5 for Summarization using 🤗 Transformers and Amazon SageMaker - - Open on Github diff --git a/sagemaker-huggingface-llm.md b/sagemaker-huggingface-llm.md index 39ac041429..2072e7f4fb 100644 --- a/sagemaker-huggingface-llm.md +++ b/sagemaker-huggingface-llm.md @@ -7,8 +7,6 @@ authors: # Introducing the Hugging Face LLM Inference Container for Amazon SageMaker - - This is an example on how to deploy the open-source LLMs, like [BLOOM](https://huggingface.co/bigscience/bloom) to Amazon SageMaker for inference using the new Hugging Face LLM Inference Container. We will deploy the 12B [Pythia Open Assistant Model](https://huggingface.co/OpenAssistant/pythia-12b-sft-v8-7k-steps), an open-source Chat LLM trained with the Open Assistant dataset. diff --git a/sasha-luccioni-interview.md b/sasha-luccioni-interview.md index 05cff81db8..de0419216c 100644 --- a/sasha-luccioni-interview.md +++ b/sasha-luccioni-interview.md @@ -5,10 +5,8 @@ authors: - user: britneymuller --- -

Machine Learning Experts - Sasha Luccioni

+# Machine Learning Experts - Sasha Luccioni - - ## 🤗 Welcome to Machine Learning Experts - Sasha Luccioni diff --git a/sb3.md b/sb3.md index c942c14770..cb1b84ce40 100644 --- a/sb3.md +++ b/sb3.md @@ -7,8 +7,6 @@ authors: # Welcome Stable-baselines3 to the Hugging Face Hub 🤗 - - 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/sd_distillation.md b/sd_distillation.md index ad02d2f898..ea358a76c9 100644 --- a/sd_distillation.md +++ b/sd_distillation.md @@ -10,10 +10,8 @@ authors: guest: true --- -

Open-sourcing Knowledge Distillation Code and Weights of SD-Small and SD-Tiny

+# Open-sourcing Knowledge Distillation Code and Weights of SD-Small and SD-Tiny - -

diff --git a/searching-the-hub.md b/searching-the-hub.md index 613587b509..bd2cb79e12 100644 --- a/searching-the-hub.md +++ b/searching-the-hub.md @@ -7,8 +7,6 @@ authors: # Supercharged Searching on the Hugging Face Hub - - Open In Colab diff --git a/sempre-health-eap-case-study.md b/sempre-health-eap-case-study.md index 694c3a81fe..4ae1e61809 100644 --- a/sempre-health-eap-case-study.md +++ b/sempre-health-eap-case-study.md @@ -5,10 +5,8 @@ authors: - user: huggingface --- -

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

+# How Sempre Health is leveraging the Expert Acceleration Program to accelerate their ML roadmap - - 👋 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 74db4b1ade..9aed4e32f7 100644 --- a/sentence-transformers-in-the-hub.md +++ b/sentence-transformers-in-the-hub.md @@ -7,8 +7,6 @@ authors: # Sentence Transformers in the Hugging Face Hub - - 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 0a3d575785..e9f51b7b36 100644 --- a/sentiment-analysis-fhe.md +++ b/sentiment-analysis-fhe.md @@ -8,8 +8,6 @@ authors: # Sentiment Analysis on Encrypted Data with Homomorphic Encryption - - 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 f08d549d11..d96cf23181 100644 --- a/sentiment-analysis-python.md +++ b/sentiment-analysis-python.md @@ -5,10 +5,8 @@ authors: - user: federicopascual --- -

Getting Started with Sentiment Analysis using Python

+# Getting Started with Sentiment Analysis using Python - - diff --git a/sentiment-analysis-twitter.md b/sentiment-analysis-twitter.md index b0de3a518a..fd1197f8e1 100644 --- a/sentiment-analysis-twitter.md +++ b/sentiment-analysis-twitter.md @@ -5,10 +5,8 @@ authors: - user: federicopascual --- -

Getting Started with Sentiment Analysis on Twitter

+# Getting Started with Sentiment Analysis on Twitter - - diff --git a/series-c.md b/series-c.md index 51f9ae48f4..75e08e76de 100644 --- a/series-c.md +++ b/series-c.md @@ -5,10 +5,8 @@ authors: - user: huggingface --- -

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

+# We Raised $100 Million for Open & Collaborative Machine Learning 🚀 - - 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 910ff5f2c0..dbdd49f04f 100644 --- a/setfit.md +++ b/setfit.md @@ -10,10 +10,8 @@ authors: - user: moshew --- -

SetFit: Efficient Few-Shot Learning Without Prompts

+# SetFit: Efficient Few-Shot Learning Without Prompts - - diff --git a/simple-considerations.md b/simple-considerations.md index dd7ca2e0b4..8ca5441cbb 100644 --- a/simple-considerations.md +++ b/simple-considerations.md @@ -11,8 +11,6 @@ authors: # 🚧 Simple considerations for simple people building fancy neural networks - - 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 11879cd821..dd565ed59e 100644 --- a/skops.md +++ b/skops.md @@ -9,8 +9,6 @@ authors: # Introducing Skops - - ## Introducing Skops diff --git a/snorkel-case-study.md b/snorkel-case-study.md index adda47b4e9..9e40ebafce 100644 --- a/snorkel-case-study.md +++ b/snorkel-case-study.md @@ -5,11 +5,9 @@ authors: - user: VioletteLepercq --- -

Snorkel AI x Hugging Face: unlock foundation models for enterprises

+# Snorkel AI x Hugging Face: unlock foundation models for enterprises - - _This article is a cross-post from an originally published post on April 6, 2023 [in Snorkel's blog](https://snorkel.ai/snorkel-hugging-face-unlock-foundation-models-for-enterprise/), by Friea Berg ._ diff --git a/snowball-fight.md b/snowball-fight.md index bfcbfd4095..79da8169d5 100644 --- a/snowball-fight.md +++ b/snowball-fight.md @@ -7,8 +7,6 @@ authors: # Introducing Snowball Fight ☃️, our First ML-Agents Environment - - diff --git a/spaces_3dmoljs.md b/spaces_3dmoljs.md index 36f3db143b..ad12d12f1b 100644 --- a/spaces_3dmoljs.md +++ b/spaces_3dmoljs.md @@ -6,10 +6,8 @@ authors: guest: true --- -

Visualize proteins on Hugging Face Spaces

+# Visualize proteins on Hugging Face Spaces - - 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 f64931869f..6cc5cd4236 100644 --- a/spacy.md +++ b/spacy.md @@ -9,8 +9,6 @@ authors: # Welcome spaCy to the Hugging Face Hub - - [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/speecht5.md b/speecht5.md index 72bf7d7f4b..cd5b0acc21 100644 --- a/speecht5.md +++ b/speecht5.md @@ -7,8 +7,6 @@ authors: # Speech Synthesis, Recognition, and More With SpeechT5 - - We’re happy to announce that SpeechT5 is now available in 🤗 Transformers, an open-source library that offers easy-to-use implementations of state-of-the-art machine learning models. diff --git a/stable-diffusion-finetuning-intel.md b/stable-diffusion-finetuning-intel.md index f50fbdc412..7e20067897 100644 --- a/stable-diffusion-finetuning-intel.md +++ b/stable-diffusion-finetuning-intel.md @@ -8,8 +8,6 @@ authors: # Fine-tuning Stable Diffusion Models on Intel CPUs - - Diffusion models helped popularize generative AI thanks to their uncanny ability to generate photorealistic images from text prompts. These models have now found their way into enterprise use cases like synthetic data generation or content creation. The Hugging Face hub includes over 5,000 pre-trained text-to-image [models](https://huggingface.co/models?pipeline_tag=text-to-image&sort=trending). Combining them with the [Diffusers library](https://huggingface.co/docs/diffusers/index), it's never been easier to start experimenting and building image generation workflows. diff --git a/stable-diffusion-inference-intel.md b/stable-diffusion-inference-intel.md index c8b4e96251..c91f76a823 100644 --- a/stable-diffusion-inference-intel.md +++ b/stable-diffusion-inference-intel.md @@ -9,8 +9,6 @@ authors: # Accelerating Stable Diffusion Inference on Intel CPUs - - Recently, we introduced the latest generation of [Intel Xeon](https://www.intel.com/content/www/us/en/products/details/processors/xeon/scalable.html) CPUs (code name Sapphire Rapids), its new hardware features for deep learning acceleration, and how to use them to accelerate [distributed fine-tuning](https://huggingface.co/blog/intel-sapphire-rapids) and [inference](https://huggingface.co/blog/intel-sapphire-rapids-inference) for natural language processing Transformers. diff --git a/stable-diffusion-xl-coreml.md b/stable-diffusion-xl-coreml.md index 679102ef24..6576ed0735 100644 --- a/stable-diffusion-xl-coreml.md +++ b/stable-diffusion-xl-coreml.md @@ -9,8 +9,6 @@ authors: # Stable Diffusion XL on Mac with Advanced Core ML Quantization - - [Stable Diffusion XL](https://stability.ai/stablediffusion) was released yesterday and it’s awesome. It can generate large (1024x1024) high quality images; adherence to prompts has been improved with some new tricks; it can effortlessly produce very dark or very bright images thanks to the latest research on noise schedulers; and it’s open source! diff --git a/stable_diffusion.md b/stable_diffusion.md index b255e29434..bac91d878c 100644 --- a/stable_diffusion.md +++ b/stable_diffusion.md @@ -10,8 +10,6 @@ authors: # Stable Diffusion with 🧨 Diffusers - - Open In Colab diff --git a/stable_diffusion_jax.md b/stable_diffusion_jax.md index b67b57f083..8b37426933 100644 --- a/stable_diffusion_jax.md +++ b/stable_diffusion_jax.md @@ -8,8 +8,6 @@ authors: # 🧨 Stable Diffusion in JAX / Flax ! - - Open In Colab diff --git a/stackllama.md b/stackllama.md index 8c7ce74a44..bce26d7b2a 100644 --- a/stackllama.md +++ b/stackllama.md @@ -13,8 +13,6 @@ authors: # StackLLaMA: A hands-on guide to train LLaMA with RLHF - - Models such as [ChatGPT]([https://openai.com/blog/chatgpt](https://openai.com/blog/chatgpt)), [GPT-4]([https://openai.com/research/gpt-4](https://openai.com/research/gpt-4)), and [Claude]([https://www.anthropic.com/index/introducing-claude](https://www.anthropic.com/index/introducing-claude)) are powerful language models that have been fine-tuned using a method called Reinforcement Learning from Human Feedback (RLHF) to be better aligned with how we expect them to behave and would like to use them. diff --git a/starchat-alpha.md b/starchat-alpha.md index 6865402a6e..72e3f604f4 100644 --- a/starchat-alpha.md +++ b/starchat-alpha.md @@ -15,8 +15,6 @@ authors: # Creating a Coding Assistant with StarCoder - - If you’re a software developer, chances are that you’ve used GitHub Copilot or ChatGPT to solve programming tasks such as translating code from one language to another or generating a full implementation from a natural language query like *“Write a Python program to find the Nth Fibonacci number”*. Although impressive in their capabilities, these proprietary systems typically come with several drawbacks, including a lack of transparency on the public data used to train them and the inability to adapt them to your domain or codebase. diff --git a/starcoder.md b/starcoder.md index 669fb56dc8..0ab93881cf 100644 --- a/starcoder.md +++ b/starcoder.md @@ -8,8 +8,6 @@ authors: # StarCoder: A State-of-the-Art LLM for Code - - ## Introducing StarCoder diff --git a/streamlit-spaces.md b/streamlit-spaces.md index bce8f8923d..b2f5718ad7 100644 --- a/streamlit-spaces.md +++ b/streamlit-spaces.md @@ -8,8 +8,6 @@ authors: # Hosting your Models and Datasets on Hugging Face Spaces using Streamlit - - diff --git a/summer-at-huggingface.md b/summer-at-huggingface.md index e489a1c69f..6cde113df0 100644 --- a/summer-at-huggingface.md +++ b/summer-at-huggingface.md @@ -8,8 +8,6 @@ authors: # Summer At Hugging Face 😎 - - 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 bc041dec02..0d3da5d52e 100644 --- a/supercharge-customer-service-with-machine-learning.md +++ b/supercharge-customer-service-with-machine-learning.md @@ -7,8 +7,6 @@ authors: # Supercharged Customer Service with Machine Learning - - Open In Colab diff --git a/swift-coreml-llm.md b/swift-coreml-llm.md index 48771ca9b2..b8e92e7690 100644 --- a/swift-coreml-llm.md +++ b/swift-coreml-llm.md @@ -7,8 +7,6 @@ authors: # Releasing Swift Transformers: Run On-Device LLMs in Apple Devices - - I have a lot of respect for iOS/Mac developers. I started writing apps for iPhones in 2007, when not even APIs or documentation existed. The new devices adopted some unfamiliar decisions in the constraint space, with a combination of power, screen real estate, UI idioms, network access, persistence, and latency that was different to what we were used to before. Yet, this community soon managed to create top-notch applications that felt at home with the new paradigm. diff --git a/t2i-sdxl-adapters.md b/t2i-sdxl-adapters.md index 9a5e3f89d5..a7ba819adf 100644 --- a/t2i-sdxl-adapters.md +++ b/t2i-sdxl-adapters.md @@ -13,8 +13,6 @@ authors: # Efficient Controllable Generation for SDXL with T2I-Adapters - -

diff --git a/tapex.md b/tapex.md index 6098c980a5..e7948c0182 100644 --- a/tapex.md +++ b/tapex.md @@ -9,8 +9,6 @@ authors: # Efficient Table Pre-training without Real Data: An Introduction to TAPEX - - 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 e5fb0ce44b..48179d9a36 100644 --- a/tensorflow-philosophy.md +++ b/tensorflow-philosophy.md @@ -7,8 +7,6 @@ authors: # Hugging Face's TensorFlow Philosophy - - ### Introduction diff --git a/text-to-video.md b/text-to-video.md index 6a86c83770..0e69edc529 100644 --- a/text-to-video.md +++ b/text-to-video.md @@ -5,10 +5,8 @@ authors: - user: adirik --- -

Text-to-Video: The Task, Challenges and the Current State

+# Text-to-Video: The Task, Challenges and the Current State - -

video-samples
diff --git a/text-to-webapp.md b/text-to-webapp.md index a07e55aed9..0a7b0422fe 100644 --- a/text-to-webapp.md +++ b/text-to-webapp.md @@ -7,8 +7,6 @@ authors: # Making a web app generator with open ML models - - As more code generation models become publicly available, it is now possible to do text-to-web and even text-to-app in ways that we couldn't imagine before. diff --git a/tf-serving-vision.md b/tf-serving-vision.md index d5ce6abea1..24e44dc34b 100644 --- a/tf-serving-vision.md +++ b/tf-serving-vision.md @@ -8,8 +8,6 @@ authors: # Deploying TensorFlow Vision Models in Hugging Face with TF Serving - - Open In Colab diff --git a/tf-serving.md b/tf-serving.md index 0d78f1de1d..ed4f258ae8 100644 --- a/tf-serving.md +++ b/tf-serving.md @@ -5,10 +5,8 @@ authors: - user: jplu --- -

Faster TensorFlow models in Hugging Face Transformers

+# Faster TensorFlow models in Hugging Face Transformers - - Open In Colab diff --git a/tf-xla-generate.md b/tf-xla-generate.md index e0fe322b41..84f2177200 100644 --- a/tf-xla-generate.md +++ b/tf-xla-generate.md @@ -7,8 +7,6 @@ authors: # Faster Text Generation with TensorFlow and XLA - - 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/tf_tpu.md b/tf_tpu.md index 69fd97d354..2f40eac56a 100644 --- a/tf_tpu.md +++ b/tf_tpu.md @@ -8,8 +8,6 @@ authors: # Training a language model with 🤗 Transformers using TensorFlow and TPUs - - ## Introduction diff --git a/the-age-of-ml-as-code.md b/the-age-of-ml-as-code.md index afc9a14bd3..c3bd06a524 100644 --- a/the-age-of-ml-as-code.md +++ b/the-age-of-ml-as-code.md @@ -8,8 +8,6 @@ authors: # The Age of Machine Learning As Code Has Arrived - - diff --git a/time-series-transformers.md b/time-series-transformers.md index 19004dbeea..4b4378ba90 100644 --- a/time-series-transformers.md +++ b/time-series-transformers.md @@ -6,10 +6,8 @@ authors: - user: kashif --- -

Probabilistic Time Series Forecasting with 🤗 Transformers

+# Probabilistic Time Series Forecasting with 🤗 Transformers - - diff --git a/train-decision-transformers.md b/train-decision-transformers.md index 8d9fad5880..dfbc349cde 100644 --- a/train-decision-transformers.md +++ b/train-decision-transformers.md @@ -8,8 +8,6 @@ authors: # Train your first Decision Transformer - - 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/train-optimize-sd-intel.md b/train-optimize-sd-intel.md index 9f9cc75fe5..a1052abd2e 100644 --- a/train-optimize-sd-intel.md +++ b/train-optimize-sd-intel.md @@ -14,8 +14,6 @@ authors: # Optimizing Stable Diffusion for Intel CPUs with NNCF and 🤗 Optimum - - [**Latent Diffusion models**](https://arxiv.org/abs/2112.10752) are game changers when it comes to solving text-to-image generation problems. [**Stable Diffusion**](https://stability.ai/blog/stable-diffusion-public-release) is one of the most famous examples that got wide adoption in the community and industry. The idea behind the Stable Diffusion model is simple and compelling: you generate an image from a noise vector in multiple small steps refining the noise to a latent image representation. This approach works very well, but it can take a long time to generate an image if you do not have access to powerful GPUs. diff --git a/train-your-controlnet.md b/train-your-controlnet.md index c95c9dcef9..d06cdf01f8 100644 --- a/train-your-controlnet.md +++ b/train-your-controlnet.md @@ -8,8 +8,6 @@ authors: # Train your ControlNet with diffusers 🧨 - - ## Introduction [ControlNet](https://huggingface.co/blog/controlnet) is a neural network structure that allows fine-grained control of diffusion models by adding extra conditions. The technique debuted with the paper [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543), and quickly took over the open-source diffusion community author's release of 8 different conditions to control Stable Diffusion v1-5, including pose estimations, depth maps, canny edges, sketches, [and more](https://huggingface.co/lllyasviel). diff --git a/transformers-design-philosophy.md b/transformers-design-philosophy.md index 7a5264b066..9461ccc834 100644 --- a/transformers-design-philosophy.md +++ b/transformers-design-philosophy.md @@ -5,13 +5,9 @@ authors: - user: patrickvonplaten --- -

- Don't Repeat Yourself \\( {}^{\textbf{*}} \\) -

Designing open-source libraries for modern machine learning
-

+# ~~Don't~~ Repeat Yourself* - - +##### *Designing open-source libraries for modern machine learning* ## 🤗 Transformers Design Philosophy diff --git a/trl-ddpo.md b/trl-ddpo.md index a40b5297bf..a862b728eb 100644 --- a/trl-ddpo.md +++ b/trl-ddpo.md @@ -11,8 +11,6 @@ authors: # Finetune Stable Diffusion Models with DDPO via TRL - - ## Introduction diff --git a/trl-peft.md b/trl-peft.md index 316ada0de7..c6a33159be 100644 --- a/trl-peft.md +++ b/trl-peft.md @@ -12,8 +12,6 @@ authors: # Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU - - We are excited to officially release the integration of `trl` with `peft` to make Large Language Model (LLM) fine-tuning with Reinforcement Learning more accessible to anyone! In this post, we explain why this is a competitive alternative to existing fine-tuning approaches. diff --git a/unity-api.md b/unity-api.md index e998c69a35..563f880cf4 100644 --- a/unity-api.md +++ b/unity-api.md @@ -5,9 +5,8 @@ authors: - user: dylanebert --- -

How to Install and Use the Hugging Face Unity API

+# How to Install and Use the Hugging Face Unity API - The [Hugging Face Unity API](https://github.com/huggingface/unity-api) is an easy-to-use integration of the [Hugging Face Inference API](https://huggingface.co/inference-api), allowing developers to access and use Hugging Face AI models in their Unity projects. In this blog post, we'll walk through the steps to install and use the Hugging Face Unity API. diff --git a/unity-asr.md b/unity-asr.md index 79e7283b23..8cc57899e8 100644 --- a/unity-asr.md +++ b/unity-asr.md @@ -5,10 +5,8 @@ authors: - user: dylanebert --- -

AI Speech Recognition in Unity

+# AI Speech Recognition in Unity - - [![Open Source AI Game Jam](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/124_ml-for-games/gamejambanner.png)](https://itch.io/jam/open-source-ai-game-jam) diff --git a/unity-in-spaces.md b/unity-in-spaces.md index 8ed8b1ddd1..b465db8a5f 100644 --- a/unity-in-spaces.md +++ b/unity-in-spaces.md @@ -5,9 +5,8 @@ authors: - user: dylanebert --- -

How to host a Unity game in a Space

+# How to host a Unity game in a Space - diff --git a/us-national-ai-research-resource.md b/us-national-ai-research-resource.md index c2b40d57c9..52b70b32ed 100644 --- a/us-national-ai-research-resource.md +++ b/us-national-ai-research-resource.md @@ -7,8 +7,6 @@ authors: # AI Policy @🤗: Comments on U.S. National AI Research Resource Interim Report - - 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/using-ml-for-disasters.md b/using-ml-for-disasters.md index 2e67f81522..8fd73dfec2 100644 --- a/using-ml-for-disasters.md +++ b/using-ml-for-disasters.md @@ -8,8 +8,6 @@ authors: # Using Machine Learning to Aid Survivors and Race through Time - - On February 6, 2023, earthquakes measuring 7.7 and 7.6 hit South Eastern Turkey, affecting 10 cities and resulting in more than 42,000 deaths and 120,000 injured as of February 21. diff --git a/vision-transformers.md b/vision-transformers.md index b7e1b5b3d3..d72ff3bac3 100644 --- a/vision-transformers.md +++ b/vision-transformers.md @@ -5,10 +5,8 @@ authors: - user: juliensimon --- -

Deep Dive: Vision Transformers On Hugging Face Optimum Graphcore

+# Deep Dive: Vision Transformers On Hugging Face Optimum Graphcore - - 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 8a6fc64e9d..ef1ef4c41d 100644 --- a/vision_language_pretraining.md +++ b/vision_language_pretraining.md @@ -8,8 +8,6 @@ authors: # 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/vit-align.md b/vit-align.md index 159d5a3846..d0e197cce2 100644 --- a/vit-align.md +++ b/vit-align.md @@ -11,8 +11,6 @@ authors: # Kakao Brain’s Open Source ViT, ALIGN, and the New COYO Text-Image Dataset - - Kakao Brain and Hugging Face are excited to release a new open-source image-text dataset [COYO](https://github.com/kakaobrain/coyo-dataset) of 700 million pairs and two new visual language models trained on it, [ViT](https://github.com/kakaobrain/coyo-vit) and [ALIGN](https://github.com/kakaobrain/coyo-align). This is the first time ever the ALIGN model is made public for free and open-source use and the first release of ViT and ALIGN models that come with the train dataset. diff --git a/vq-diffusion.md b/vq-diffusion.md index 16c4ca5905..8f69f16064 100644 --- a/vq-diffusion.md +++ b/vq-diffusion.md @@ -7,8 +7,6 @@ authors: # VQ-Diffusion - - 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 c9ec4b1fb4..9be71e452c 100644 --- a/warm-starting-encoder-decoder.md +++ b/warm-starting-encoder-decoder.md @@ -7,8 +7,6 @@ authors: # Leveraging Pre-trained Language Model Checkpoints for Encoder-Decoder Models - - Open In Colab diff --git a/wav2vec2-with-ngram.md b/wav2vec2-with-ngram.md index 4938526831..c799e450a2 100644 --- a/wav2vec2-with-ngram.md +++ b/wav2vec2-with-ngram.md @@ -7,8 +7,6 @@ authors: # Boosting Wav2Vec2 with n-grams in 🤗 Transformers - - Open In Colab diff --git a/writer-case-study.md b/writer-case-study.md index 228c29c02b..112357136e 100644 --- a/writer-case-study.md +++ b/writer-case-study.md @@ -7,10 +7,8 @@ authors: guest: true --- -

Leveraging Hugging Face for complex generative AI use casess

+# Leveraging Hugging Face for complex generative AI use casess - - In this conversation, Jeff Boudier asks Waseem Alshikh, Co-founder and CTO of Writer, about their journey from a Hugging Face user, to a customer and now an open source model contributor. diff --git a/wuerstchen.md b/wuerstchen.md index a204775317..dbc9592c85 100644 --- a/wuerstchen.md +++ b/wuerstchen.md @@ -13,8 +13,6 @@ authors: # Introducing Würstchen: Fast Diffusion for Image Generation - - ![Collage of images created with Würstchen](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/wuertschen/collage_compressed.jpg) diff --git a/your-first-ml-project.md b/your-first-ml-project.md index ec51d5322b..c6014929ac 100644 --- a/your-first-ml-project.md +++ b/your-first-ml-project.md @@ -7,8 +7,6 @@ authors: # Liftoff! How to get started with your first ML project 🚀 - - 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 0078f069c7..75cb1c3868 100644 --- a/zero-deepspeed-fairscale.md +++ b/zero-deepspeed-fairscale.md @@ -6,10 +6,8 @@ authors: guest: true --- -

Fit More and Train Faster With ZeRO via DeepSpeed and FairScale

+# Fit More and Train Faster With ZeRO via DeepSpeed and FairScale - - ##### 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 e9553df6d1..25fa4cc270 100644 --- a/zero-shot-eval-on-the-hub.md +++ b/zero-shot-eval-on-the-hub.md @@ -11,8 +11,6 @@ authors: # Very Large Language Models and How to Evaluate Them - - Large language models can now be evaluated on zero-shot classification tasks with [Evaluation on the Hub](https://huggingface.co/spaces/autoevaluate/model-evaluator)! diff --git a/zh/_policy-ntia-rfc.md b/zh/_policy-ntia-rfc.md index 92f656862e..81a6b4354f 100644 --- a/zh/_policy-ntia-rfc.md +++ b/zh/_policy-ntia-rfc.md @@ -11,7 +11,7 @@ translators: proofreader: true --- -

人工智能政策@🤗: 回应美国国家电信和信息管理局 (NTIA) 关于人工智能问责制的评论请求

+# 人工智能政策@🤗: 回应美国国家电信和信息管理局 (NTIA) 关于人工智能问责制的评论请求 6 月 12 日，Hugging Face 向美国国家电信和信息管理局 NTIA 提交了一份关于 AI 责任政策的信息请求回应。在我们的回应中，我们强调了文档和透明度规范在推动 AI 责任过程中的作用，以及依赖此技术众多利益相关者的全面专业知识、观点和技能来应对这项技术前所未有的增长带来的任何单一实体都无法回答的更多问题之必要性。 @@ -25,5 +25,4 @@ Hugging Face 的使命是 [“民主化优秀的机器学习”](https://hugging 我们相信，优先考虑机器学习组件本身和评估结果的透明度对于实现这些目标至关重要。你可以在 这里 找到我们更详细的回应。 - \ No newline at end of file diff --git a/zh/accelerated-inference.md b/zh/accelerated-inference.md index 890262b7c2..9b784ce7c7 100644 --- a/zh/accelerated-inference.md +++ b/zh/accelerated-inference.md @@ -7,9 +7,8 @@ translators: proofreader: true --- -

如何成功将 🤗 API 客户的 transformer 模型推理速度加快 100 倍

+# 如何成功将 🤗 API 客户的 transformer 模型推理速度加快 100 倍 - 🤗 Transformers 已成为世界各地数据科学家用以探索最先进 NLP 模型、构建新 NLP 模块的默认库。它拥有超过 5000 个预训练和微调的模型，支持 250 多种语言，任君取用。无论你使用哪种框架，都能用得上它。 diff --git a/zh/aivsai.md b/zh/aivsai.md index c18e2aabc5..0dcab04c8a 100644 --- a/zh/aivsai.md +++ b/zh/aivsai.md @@ -9,8 +9,6 @@ translators: --- # AI 大战 AI，一个深度强化学习多智能体竞赛系统 - -
Thumbnail diff --git a/zh/assisted-generation.md b/zh/assisted-generation.md index 62c846190b..11e07567e3 100644 --- a/zh/assisted-generation.md +++ b/zh/assisted-generation.md @@ -11,8 +11,6 @@ translators: # 辅助生成: 低延迟文本生成的新方向 - - 大型语言模型如今风靡一时，许多公司投入大量资源来扩展它们规模并解锁新功能。然而，作为注意力持续时间不断缩短的人类，我们并不喜欢大模型缓慢的响应时间。由于延迟对于良好的用户体验至关重要，人们通常使用较小的模型来完成任务，尽管它们的质量较低 (例如 [代码补全任务](https://ai.googleblog.com/2022/07/ml-enhanced-code-completion-improves.html))。 diff --git a/zh/autoformer.md b/zh/autoformer.md index eff63c0ab0..06f6c1a038 100644 --- a/zh/autoformer.md +++ b/zh/autoformer.md @@ -14,8 +14,6 @@ translators: # Transformer 模型能够有效地进行时间序列预测 (使用 Autoformer) - - diff --git a/zh/blip-2.md b/zh/blip-2.md index 858ba9acc9..352283874e 100644 --- a/zh/blip-2.md +++ b/zh/blip-2.md @@ -12,8 +12,6 @@ translators: # 使用 BLIP-2 零样本“图生文” - - 本文将介绍来自 Salesforce 研究院的 [BLIP-2](https://huggingface.co/docs/transformers/main/en/model_doc/blip-2) 模型，它支持一整套最先进的视觉语言模型，且已集成入 [🤗 Transformers](https://huggingface.co/transformers)。我们将向你展示如何将其用于图像字幕生成、有提示图像字幕生成、视觉问答及基于聊天的提示这些应用场景。 diff --git a/zh/bloom-inference-optimization.md b/zh/bloom-inference-optimization.md index 2a7fd9f4bd..c05a743200 100644 --- a/zh/bloom-inference-optimization.md +++ b/zh/bloom-inference-optimization.md @@ -7,9 +7,7 @@ translators: - user: MatrixYao --- -

优化故事: BLOOM 模型推理

- - +# 优化故事: BLOOM 模型推理 diff --git a/zh/bloom-inference-pytorch-scripts.md b/zh/bloom-inference-pytorch-scripts.md index 8d16587672..b9ece7d750 100644 --- a/zh/bloom-inference-pytorch-scripts.md +++ b/zh/bloom-inference-pytorch-scripts.md @@ -12,8 +12,6 @@ translators: # 使用 DeepSpeed 和 Accelerate 进行超快 BLOOM 模型推理 - - 本文展示了如何使用 1760 亿 (176B) 参数的 [BLOOM 模型](https://huggingface.co/bigscience/bloom) 生成文本时如何获得超快的词吞吐 (per token throughput)。 diff --git a/zh/bloom-megatron-deepspeed.md b/zh/bloom-megatron-deepspeed.md index 53d2d777d3..a6a4e48ee6 100644 --- a/zh/bloom-megatron-deepspeed.md +++ b/zh/bloom-megatron-deepspeed.md @@ -9,10 +9,8 @@ translators: proofreader: true --- -

千亿参数开源大模型 BLOOM 背后的技术

+# 千亿参数开源大模型 BLOOM 背后的技术 - - > 假设你现在有了数据，也搞到了预算，一切就绪，准备开始训练一个大模型，一显身手了，“一朝看尽长安花”似乎近在眼前 …… 且慢！训练可不仅仅像这两个字的发音那么简单，看看 BLOOM 的训练或许对你有帮助。 diff --git a/zh/bridgetower.md b/zh/bridgetower.md index 886e46694c..34ebcf416f 100644 --- a/zh/bridgetower.md +++ b/zh/bridgetower.md @@ -13,8 +13,6 @@ translators: # 使用 Habana Gaudi2 加速视觉语言模型 BridgeTower - - 在对最先进的视觉语言模型 BridgeTower 进行微调时，使用 [Optimum Habana v1.6](https://github.com/huggingface/optimum-habana/tree/main)， Habana Gaudi2 可以达到 **近 3 倍于 A100 的速度**。硬件加速的数据加载以及 `fast DDP` 这两个新特性对性能提高贡献最大。 diff --git a/zh/chinese-language-blog.md b/zh/chinese-language-blog.md index 352ce8d79d..f7d4311374 100644 --- a/zh/chinese-language-blog.md +++ b/zh/chinese-language-blog.md @@ -9,10 +9,8 @@ authors: guest: true --- -

Hugging Face 中文博客正式发布！

+# Hugging Face 中文博客正式发布！ - - Hugging Face 的中国社区成立已经有五个月之久，我们非常高兴地看到 Hugging Face 相关的中文内容在各个平台广受好评。同时我们也注意到，Hugging Face Hub 和开源生态上有众多国内开发者们的创新和贡献。 diff --git a/zh/codellama.md b/zh/codellama.md index 683ab53feb..a127a65f80 100644 --- a/zh/codellama.md +++ b/zh/codellama.md @@ -18,8 +18,6 @@ translators: # Code Llama: Llama 2 学会写代码了！ - - ## 引言 diff --git a/zh/constrained-beam-search.md b/zh/constrained-beam-search.md index c3c9c57b1a..05bac109eb 100644 --- a/zh/constrained-beam-search.md +++ b/zh/constrained-beam-search.md @@ -12,8 +12,6 @@ translators: # 在 🤗 Transformers 中使用约束波束搜索引导文本生成 - - 在 Colab 中打开 diff --git a/zh/controlnet.md b/zh/controlnet.md index e1135b86bc..92f459ffbd 100644 --- a/zh/controlnet.md +++ b/zh/controlnet.md @@ -11,8 +11,6 @@ translators: # 使用 🧨 Diffusers 实现 ControlNet 高速推理 - - Open In Colab diff --git a/zh/cv_state.md b/zh/cv_state.md index 85356f79b2..03eba59fce 100644 --- a/zh/cv_state.md +++ b/zh/cv_state.md @@ -7,8 +7,6 @@ authors: # Hugging Face 中计算机视觉的现状 - - 在Hugging Face上，我们为与社区一起推动人工智能领域的民主化而感到自豪。作为这个使命的一部分，我们从去年开始专注于计算机视觉。开始只是 [🤗 Transformers中Vision Transformers (ViT) 的一个 PR](https://github.com/huggingface/transformers/pull/10950)，现在已经发展壮大：8个核心视觉任务，超过3000个模型，在Hugging Face Hub上有超过1000个数据集。 diff --git a/zh/dedup.md b/zh/dedup.md index 5bc14835e7..be0276d0e6 100644 --- a/zh/dedup.md +++ b/zh/dedup.md @@ -11,8 +11,6 @@ translators: # BigCode 背后的大规模数据去重 - - ## 目标受众 diff --git a/zh/deploy-deepfloydif-using-bentoml.md b/zh/deploy-deepfloydif-using-bentoml.md index ebb3c495af..05aba593d1 100644 --- a/zh/deploy-deepfloydif-using-bentoml.md +++ b/zh/deploy-deepfloydif-using-bentoml.md @@ -12,8 +12,6 @@ translators: # 使用 BentoML 部署 🤗 Hugging Face 上的模型：DeepFloyd IF 实战 - - Hugging Face 的 Model Hub 可以让我们轻松地上传、分享和部署模型，为开发者们节省了从头开始训练模型所需的时间和计算资源。然而，在真实世界的生产环境中或以云原生的方式部署模型则仍然可能带来挑战。 diff --git a/zh/dialog-agents.md b/zh/dialog-agents.md index 2f67fd5acb..59c1be71c1 100644 --- a/zh/dialog-agents.md +++ b/zh/dialog-agents.md @@ -15,8 +15,6 @@ translators: # 是什么让对话代理有用？ ## ChatGPT 背后的技术：RLHF、IFT、CoT、红蓝对抗等 - - 近段时间，ChatGPT 横空出世并获得巨大成功，使得 RLHF、SFT、IFT、CoT 等这些晦涩的缩写开始出现在普罗大众的讨论中。这些晦涩的首字母缩略词究竟是什么意思？为什么它们如此重要？我们调查了相关的所有重要论文，以对这些工作进行分类，总结迄今为止的工作，并对后续工作进行展望。 diff --git a/zh/diffusers-turns-1.md b/zh/diffusers-turns-1.md index 210d3f8c67..de2bcd4c8d 100644 --- a/zh/diffusers-turns-1.md +++ b/zh/diffusers-turns-1.md @@ -13,8 +13,6 @@ translators: # 🤗 Diffusers 一岁啦 ! - - 十分高兴 🤗 Diffusers 迎来它的一岁生日！这是令人激动的一年，感谢社区和开源贡献者，我们对我们的工作感到十分骄傲和自豪。去年，文本到图像的模型，如 DALL-E 2, Imagen, 和 Stable Diffusion 以其从文本生成逼真的图像的能力，吸引了全世界的关注，也带动了对生成式 AI 的大量兴趣和开发工作。但是这些强大的工作不易获取。 diff --git a/zh/document-ai.md b/zh/document-ai.md index e9439ecb93..a09a55ad16 100644 --- a/zh/document-ai.md +++ b/zh/document-ai.md @@ -12,8 +12,6 @@ translators: # 加速 Document AI (文档智能) 发展 - - 在企业的数字工作流中充满了各种文档，包括信件、发票、表格、报告、收据等，我们无法自动提取它们的知识。如今随着文本、视觉和多模态人工智能的进步，我们有可能解锁这些知识，这篇文章向你展示了你的团队该如何使用开源模型来构建免费的定制化解决方案。 diff --git a/zh/dpo-trl.md b/zh/dpo-trl.md index 886ea0c0d9..3fcaf4201f 100644 --- a/zh/dpo-trl.md +++ b/zh/dpo-trl.md @@ -13,8 +13,6 @@ translators: # 使用 DPO 微调 Llama 2 - - ## 简介 diff --git a/zh/dreambooth.md b/zh/dreambooth.md index a664df148f..ed5ff0225f 100644 --- a/zh/dreambooth.md +++ b/zh/dreambooth.md @@ -14,8 +14,6 @@ translators: # 使用 Diffusers 通过 Dreambooth 技术来训练 Stable Diffusion - - [Dreambooth](https://dreambooth.github.io/) 是一种使用专门的微调形式来训练 [Stable Diffusion](https://huggingface.co/blog/stable_diffusion) 的新概念技术。一些人用他仅仅使用很少的他们的照片训练出了一个很棒的照片，有一些人用他去尝试新的风格。🧨 Diffusers 提供一个 [DreamBooth 训练脚本](https://github.com/huggingface/diffusers/tree/main/examples/DreamBooth)。这使得训练不会花费很长时间，但是他比较难筛选正确的超参数并且容易过拟合。 diff --git a/zh/elixir-bumblebee.md b/zh/elixir-bumblebee.md index 3e653d80b5..c114b2f08b 100644 --- a/zh/elixir-bumblebee.md +++ b/zh/elixir-bumblebee.md @@ -12,8 +12,6 @@ translators: # 从 GPT2 到 Stable Diffusion：Elixir 社区迎来了 Hugging Face - - 上周，[Elixir 社区](https://elixir-lang.org/) 向大家宣布，Elixir 语言社区新增从 GPT2 到 Stable Diffusion 的一系列神经网络模型。这些模型得以实现归功于 [刚刚发布的 Bumblebee 库](https://news.livebook.dev/announcing-bumblebee-gpt2-stable-diffusion-and-more-in-elixir-3Op73O)。Bumblebee 库是使用纯 Elixir 语言实现的 Hugging Face Transformers 库。 diff --git a/zh/encoder-decoder.md b/zh/encoder-decoder.md index b69f99b4d8..2d53b5cec8 100644 --- a/zh/encoder-decoder.md +++ b/zh/encoder-decoder.md @@ -7,10 +7,8 @@ translators: - user: MatrixYao --- -

基于 Transformers 的编码器-解码器模型

+# 基于 Transformers 的编码器-解码器模型 - - 在 Colab 中打开 diff --git a/zh/encrypted-llm.md b/zh/encrypted-llm.md index 8c7315733f..200f77ec28 100644 --- a/zh/encrypted-llm.md +++ b/zh/encrypted-llm.md @@ -14,8 +14,6 @@ translators: # 使用 FHE 实现加密大语言模型 - - 近来，大语言模型 (LLM) 已被证明是提高编程、内容生成、文本分析、网络搜索及远程学习等诸多领域生产力的可靠工具。 diff --git a/zh/ethics-diffusers.md b/zh/ethics-diffusers.md index bb11776d95..bee831822c 100644 --- a/zh/ethics-diffusers.md +++ b/zh/ethics-diffusers.md @@ -11,8 +11,6 @@ translators: # 开发 Diffusers 库的道德行为指南 - - 我们正在努力让我们每次发布的库更加负责！ diff --git a/zh/ethics-soc-3.md b/zh/ethics-soc-3.md index c85d92dea1..e92c728fcf 100644 --- a/zh/ethics-soc-3.md +++ b/zh/ethics-soc-3.md @@ -16,8 +16,6 @@ translators: # 道德与社会问题简报 #3: Hugging Face 上的道德开放性 - - ## 使命：开放和优秀的机器学习 在我们的使命中，我们致力于推动机器学习（ML）的民主化，我们在研究如何支持 ML 社区工作并有助于检查危害和防止可能的危害发生。开放式的发展和科学可以分散力量，让许多人集体开展反映他们需求和价值的 AI 研究工作。虽然[开放性使得更广泛的观点能够为研究和整个 AI 贡献力量，但它也面对着较小风险控制的紧张](https://arxiv.org/abs/2302.04844)。 diff --git a/zh/ethics-soc-4.md b/zh/ethics-soc-4.md index 05ab56c71f..7fc4a8afca 100644 --- a/zh/ethics-soc-4.md +++ b/zh/ethics-soc-4.md @@ -17,8 +17,6 @@ translators: # 道德与社会问题简报 #4: 文生图模型中的偏见 - - **简而言之: 我们需要更好的方法来评估文生图模型中的偏见** diff --git a/zh/evaluating-mmlu-leaderboard.md b/zh/evaluating-mmlu-leaderboard.md index e9cbbca4dc..ee868befe4 100644 --- a/zh/evaluating-mmlu-leaderboard.md +++ b/zh/evaluating-mmlu-leaderboard.md @@ -14,8 +14,6 @@ translators: # Open LLM 排行榜近况 - - Open LLM 排行榜是 Hugging Face 设立的一个用于评测开放大语言模型的公开榜单。最近，随着 [**Falcon 🦅**](https://huggingface.co/tiiuae/falcon-40b) 的发布并在 [Open LLM 排行榜](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) 上疯狂屠榜，围绕这个榜单在推特上掀起了一轮热烈的讨论。 diff --git a/zh/falcon-180b.md b/zh/falcon-180b.md index 74fef4c202..5b2546e9c4 100644 --- a/zh/falcon-180b.md +++ b/zh/falcon-180b.md @@ -11,8 +11,6 @@ authors: # Falcon 180B 登陆 Hugging Face Hub 🔥 - - ## 引言 diff --git a/zh/falcon.md b/zh/falcon.md index e04c0d8f64..b3935065b4 100644 --- a/zh/falcon.md +++ b/zh/falcon.md @@ -16,8 +16,6 @@ translators: # Falcon 登陆 Hugging Face 生态 - - ## 引言 diff --git a/zh/fine-tune-whisper.md b/zh/fine-tune-whisper.md index 71dd68733b..6f4cb8046d 100644 --- a/zh/fine-tune-whisper.md +++ b/zh/fine-tune-whisper.md @@ -11,8 +11,6 @@ translators: # 使用 🤗 Transformers 为多语种语音识别任务微调 Whisper 模型 - - 在 Colab 中打开 diff --git a/zh/game-jam-first-edition-results.md b/zh/game-jam-first-edition-results.md index b74d3ac332..3db5682c79 100644 --- a/zh/game-jam-first-edition-results.md +++ b/zh/game-jam-first-edition-results.md @@ -13,8 +13,6 @@ translators: # 首届开源 AI 游戏挑战赛事结果 - - 北京时间 7 月 8 日到 7 月 10 日， **我们举办了 [首届开源 AI 游戏开发挑战赛](https://itch.io/jam/open-source-ai-game-jam)**。这是一场激动人心的赛事活动，游戏开发者在紧迫的 48 小时内使用 AI 创造、创新有创意的游戏。 diff --git a/zh/generative-ai-models-on-intel-cpu.md b/zh/generative-ai-models-on-intel-cpu.md index 0e11a06e98..d284573571 100644 --- a/zh/generative-ai-models-on-intel-cpu.md +++ b/zh/generative-ai-models-on-intel-cpu.md @@ -11,8 +11,6 @@ translators: # 越小越好: Q8-Chat，在英特尔至强 CPU 上体验高效的生成式 AI - - 大语言模型 (LLM) 正在席卷整个机器学习世界。得益于其 [transformer](https://arxiv.org/abs/1706.03762) 架构，LLM 拥有从大量非结构化数据 (如文本、图像、视频或音频) 中学习的不可思议的能力。它们在 [多种任务类型](https://huggingface.co/tasks) 上表现非常出色，无论是文本分类之类的抽取任务 (extractive task) 还是文本摘要和文生图像之类的生成任务 (generative task)。 diff --git a/zh/getting-started-habana.md b/zh/getting-started-habana.md index a3939b19fc..b6206ba7d1 100644 --- a/zh/getting-started-habana.md +++ b/zh/getting-started-habana.md @@ -11,8 +11,6 @@ translators: # 基于 Habana Gaudi 的 Transformers 入门 - - 几周前，我们很高兴地 [宣布](https://huggingface.co/blog/zh/habana) [Habana Labs](https://habana.ai) 和 [Hugging Face](https://huggingface.co/) 将开展加速 transformer 模型的训练方面的合作。 diff --git a/zh/gptq-integration.md b/zh/gptq-integration.md index c2b71d7249..74eb4b8fd6 100644 --- a/zh/gptq-integration.md +++ b/zh/gptq-integration.md @@ -20,8 +20,6 @@ translators: # 使用 AutoGPTQ 和 transformers 让大语言模型更轻量化 - - 大语言模型在理解和生成人类水平的文字方面所展现出的非凡能力，正在许多领域带来应用上的革新。然而，在消费级硬件上训练和部署大语言模型的需求也变得越来越难以满足。 diff --git a/zh/habana-gaudi-2-benchmark.md b/zh/habana-gaudi-2-benchmark.md index c29073499a..cf05d82e5c 100644 --- a/zh/habana-gaudi-2-benchmark.md +++ b/zh/habana-gaudi-2-benchmark.md @@ -11,8 +11,6 @@ translators: # 更快的训练和推理: 对比 Habana Gaudi®2 和英伟达 A100 80GB - - 通过本文，你将学习如何使用 [Habana® Gaudi®2](https://habana.ai/training/gaudi2/) 加速模型训练和推理，以及如何使用 🤗 [Optimum Habana](https://huggingface.co/docs/optimum/habana/index) 训练更大的模型。然后，我们展示了几个基准测例，包括 BERT 预训练、Stable Diffusion 推理以及 T5-3B 微调，以评估 Gaudi1、Gaudi2 和英伟达 A100 80GB 之间的性能差异。剧透一下: Gaudi2 的训练和推理速度大约是英伟达 A100 80GB 的两倍！ diff --git a/zh/habana-gaudi-2-bloom.md b/zh/habana-gaudi-2-bloom.md index 6b37513e3f..132b51f0be 100644 --- a/zh/habana-gaudi-2-bloom.md +++ b/zh/habana-gaudi-2-bloom.md @@ -9,8 +9,6 @@ translators: # 大语言模型快速推理：在 Habana Gaudi2 上推理 BLOOMZ - - 本文将展示如何在 [Habana® Gaudi®2](https://habana.ai/training/gaudi2/) 上使用 🤗 [Optimum Habana](https://huggingface.co/docs/optimum/habana/index)。Optimum Habana 是 Gaudi2 和 🤗 Transformers 库之间的桥梁。本文设计并实现了一个大模型推理基准测试，证明了通过使用 Optimum Habana 你将能够在 Gaudi2 上获得 **比目前市面上任何可用的 GPU 都快的推理速度**。 diff --git a/zh/hf-bitsandbytes-integration.md b/zh/hf-bitsandbytes-integration.md index 9963f1b2df..9763a37588 100644 --- a/zh/hf-bitsandbytes-integration.md +++ b/zh/hf-bitsandbytes-integration.md @@ -13,8 +13,6 @@ translators: # 大规模 Transformer 模型 8 比特矩阵乘简介 - 基于 Hugging Face Transformers、Accelerate 以及 bitsandbytes - - ![thumbnail](/blog/assets/96_hf_bitsandbytes_integration/Thumbnail_blue.png) diff --git a/zh/how-to-generate.md b/zh/how-to-generate.md index 33d2300905..07e2a1a893 100644 --- a/zh/how-to-generate.md +++ b/zh/how-to-generate.md @@ -9,10 +9,8 @@ translators: proofreader: true --- -

如何生成文本: 通过 Transformers 用不同的解码方法生成文本

+# 如何生成文本: 通过 Transformers 用不同的解码方法生成文本 - - Open In Colab diff --git a/zh/idefics.md b/zh/idefics.md index 22fa9223a6..12757c58b1 100644 --- a/zh/idefics.md +++ b/zh/idefics.md @@ -24,8 +24,6 @@ translators: # IDEFICS 简介: 最先进视觉语言模型的开源复现 - - 我们很高兴发布 IDEFICS ( **I**mage-aware **D**ecoder **E**nhanced à la **F**lamingo with **I**ninterleaved **C**ross-attention **S** ) 这一开放视觉语言模型。 IDEFICS 基于 [Flamingo](https://huggingface.co/papers/2204.14198)，Flamingo 作为最先进的视觉语言模型，最初由 DeepMind 开发，但目前尚未公开发布。与 GPT-4 类似，该模型接受任意图像和文本输入序列并生成输出文本。IDEFICS 仅基于公开可用的数据和模型 (LLaMA v1 和 OpenCLIP) 构建，它有两个变体: 基础模型和指令模型。每个变体又各有 90 亿参数和 800 亿参数两个版本。 diff --git a/zh/if.md b/zh/if.md index f609c2b739..ffea1a6520 100644 --- a/zh/if.md +++ b/zh/if.md @@ -21,8 +21,6 @@ translators: Open In Colab - - **本文简介**: 本文展示了如何在免费版 Google Colab 上使用 🧨 diffusers 运行最强大的开源文本生成图片模型之一 **IF**。 diff --git a/zh/image-similarity.md b/zh/image-similarity.md index 90fb2c53c7..1810afea54 100644 --- a/zh/image-similarity.md +++ b/zh/image-similarity.md @@ -9,12 +9,7 @@ translators: proofreader: true --- -

- 基于 Hugging Face Datasets 和 Transformers 的图像相似性搜索 -

- - - +# 基于 Hugging Face Datasets 和 Transformers 的图像相似性搜索 Open In Colab diff --git a/zh/inference-endpoints-llm.md b/zh/inference-endpoints-llm.md index 186953dbf4..5e8b90e95c 100644 --- a/zh/inference-endpoints-llm.md +++ b/zh/inference-endpoints-llm.md @@ -11,8 +11,6 @@ translators: # 用 Hugging Face 推理端点部署 LLM - - 开源的 LLM，如 [Falcon](https://huggingface.co/tiiuae/falcon-40b)、[(Open-)LLaMA](https://huggingface.co/openlm-research/open_llama_13b)、[X-Gen](https://huggingface.co/Salesforce/xgen-7b-8k-base)、[StarCoder](https://huggingface.co/bigcode/starcoder) 或 [RedPajama](https://huggingface.co/togethercomputer/RedPajama-INCITE-7B-Base)，近几个月来取得了长足的进展，能够在某些用例中与闭源模型如 ChatGPT 或 GPT4 竞争。然而，有效且优化地部署这些模型仍然是一个挑战。 diff --git a/zh/inference-update.md b/zh/inference-update.md index 8b9bcf7ecc..b6e00ca00c 100644 --- a/zh/inference-update.md +++ b/zh/inference-update.md @@ -7,10 +7,8 @@ translators: - user: Johnson817 --- -

Hugging Face 提供的推理（Inference）解决方案

+# Hugging Face 提供的推理（Inference）解决方案 - - 每天，开发人员和组织都在使用 [Hugging Face 平台上托管的模型](https://huggingface.co/models)，将想法变成用作概念验证（proof-of-concept）的 demo，再将 demo 变成生产级的应用。Transformer 模型已成为广泛的机器学习（ML）应用的流行模型结构，包括自然语言处理、计算机视觉、语音等；扩散模型（Diffusers）也已成为 text-to-image、image-to-image 类生成模型的流行模型结构；其他模型结构在其他任务中也很受欢迎，而我们在 Hugging Face Hub 上提供了这些模型结构的所有信息。 diff --git a/zh/informer.md b/zh/informer.md index 0473c5f202..ca37e5f60b 100644 --- a/zh/informer.md +++ b/zh/informer.md @@ -11,8 +11,6 @@ translators: --- # 使用 Informer 进行多元概率时间序列预测 - - diff --git a/zh/instruction-tuning-sd.md b/zh/instruction-tuning-sd.md index a1e83ff7a2..c261cf6700 100644 --- a/zh/instruction-tuning-sd.md +++ b/zh/instruction-tuning-sd.md @@ -11,8 +11,6 @@ translators: # 使用 InstructPix2Pix 对 Stable Diffusion 进行指令微调 - - 本文主要探讨如何使用指令微调的方法教会 [Stable Diffusion](https://huggingface.co/blog/zh/stable_diffusion) 按照指令 PS 图像。这样，我们 Stable Diffusion 就能听得懂人话，并根据要求对输入图像进行相应操作，如: _将输入的自然图像卡通化_。 diff --git a/zh/intel-sapphire-rapids-inference.md b/zh/intel-sapphire-rapids-inference.md index 01fd2a7cfa..8e35fa5f54 100644 --- a/zh/intel-sapphire-rapids-inference.md +++ b/zh/intel-sapphire-rapids-inference.md @@ -11,8 +11,6 @@ translators: # CPU 推理 | 使用英特尔 Sapphire Rapids 加速 PyTorch Transformers - - 在 [最近的一篇文章](https://huggingface.co/blog/zh/intel-sapphire-rapids) 中，我们介绍了代号为 [Sapphire Rapids](https://en.wikipedia.org/wiki/Sapphire_Rapids) 的第四代英特尔至强 CPU 及其新的先进矩阵扩展 ([AMX](https://en.wikipedia.org/wiki/Advanced_Matrix_Extensions)) 指令集。通过使用 Amazon EC2 上的 Sapphire Rapids 服务器集群并结合相应的英特尔优化库，如 [英特尔 PyTorch 扩展](https://github.com/intel/intel-extension-for-pytorch) (IPEX)，我们展示了如何使用 CPU 进行高效的分布式大规模训练，与上一代至强 (Ice Lake) 相比，Sapphire Rapids 实现了 8 倍的加速，取得了近线性的扩展比。 diff --git a/zh/intel-sapphire-rapids.md b/zh/intel-sapphire-rapids.md index 33fa44334f..62c7a9debf 100644 --- a/zh/intel-sapphire-rapids.md +++ b/zh/intel-sapphire-rapids.md @@ -11,8 +11,6 @@ translators: # 使用英特尔 Sapphire Rapids 加速 PyTorch Transformers 模型（第一部分） - - 大约一年以前，我们 [展示](https://huggingface.co/blog/accelerating-pytorch) 了如何在第三代 [英特尔至强可扩展](https://www.intel.com/content/www/us/en/products/details/processors/xeon/scalable.html) CPU（即 Ice Lake）集群上分布式训练 Hugging Face transformers 模型。最近，英特尔发布了代号为 Sapphire Rapids 的第四代至强可扩展 CPU，该 CPU 包含了令人兴奋的深度学习加速新指令。 diff --git a/zh/intro-graphml.md b/zh/intro-graphml.md index 0bb3cb6896..f73b05e11e 100644 --- a/zh/intro-graphml.md +++ b/zh/intro-graphml.md @@ -11,8 +11,6 @@ translators: # 一文带你入门图机器学习 - - 本文主要涉及图机器学习的基础知识。 diff --git a/zh/introducing-csearch.md b/zh/introducing-csearch.md index 65e468f9d4..f01b8c59dd 100644 --- a/zh/introducing-csearch.md +++ b/zh/introducing-csearch.md @@ -9,10 +9,8 @@ translators: proofreader: true --- -

在 Transformers 中使用对比搜索生成可媲美人类水平的文本🤗

+# 在 Transformers 中使用对比搜索生成可媲美人类水平的文本🤗 - - --- diff --git a/zh/large-language-models.md b/zh/large-language-models.md index a8550b6172..7ca2b2004d 100644 --- a/zh/large-language-models.md +++ b/zh/large-language-models.md @@ -11,8 +11,6 @@ translators: # 大语言模型：新的摩尔定律？ - - 不久前，微软和 Nvidia [推出了](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，一种基于 Transformer 的模型，被誉为是 “*世界上最大且最强的生成语言模型*”。 diff --git a/zh/llama2.md b/zh/llama2.md index ba652101ce..4f7de5d378 100644 --- a/zh/llama2.md +++ b/zh/llama2.md @@ -14,8 +14,6 @@ translators: # Llama 2 来袭 - 在 Hugging Face 上玩转它 - - ## 引言 diff --git a/zh/llm-leaderboard.md b/zh/llm-leaderboard.md index c60de79a73..28225e6d7a 100644 --- a/zh/llm-leaderboard.md +++ b/zh/llm-leaderboard.md @@ -21,8 +21,6 @@ translators: # 基础大模型能像人类一样标注数据吗？ - - 自从 ChatGPT 出现以来，我们见证了大语言模型 (LLM) 领域前所未有的发展，尤其是对话类模型，经过微调以后可以根据给出的提示语 (prompt) 来完成相关要求和命令。然而，直到如今我们也无法对比这些大模型的性能，因为缺乏一个统一的基准，难以严谨地去测试它们各自的性能。评测我们发给它们的指令以及对话模型本身，从本质上来讲就很困难，毕竟用户的评价标准都是围绕对回答的质量的主观感受; 而现有的自然语言处理任务的性能评价标准，却大多局限于特定指标和某些定量标准。 diff --git a/zh/lora.md b/zh/lora.md index d95d7afe25..680b948c32 100644 --- a/zh/lora.md +++ b/zh/lora.md @@ -12,8 +12,6 @@ translators: # 使用 LoRA 进行 Stable Diffusion 的高效参数微调 - - [LoRA: Low-Rank Adaptation of Large Language Models](https://arxiv.org/abs/2106.09685) 是微软研究员引入的一项新技术，主要用于处理大模型微调的问题。目前超过数十亿以上参数的具有强能力的大模型 (例如 GPT-3) 通常在为了适应其下游任务的微调中会呈现出巨大开销。LoRA 建议冻结预训练模型的权重并在每个 Transformer 块中注入可训练层 (*秩-分解矩阵*)。因为不需要为大多数模型权重计算梯度，所以大大减少了需要训练参数的数量并且降低了 GPU 的内存要求。研究人员发现，通过聚焦大模型的 Transformer 注意力块，使用 LoRA 进行的微调质量与全模型微调相当，同时速度更快且需要更少的计算。 diff --git a/zh/mask2former.md b/zh/mask2former.md index b00b1f6fc6..4fd0a4dc38 100644 --- a/zh/mask2former.md +++ b/zh/mask2former.md @@ -11,8 +11,6 @@ translators: # 通用图像分割任务: 使用 Mask2Former 和 OneFormer - - diff --git a/zh/megatron-training.md b/zh/megatron-training.md index 1f4b3d0481..f47f33f311 100644 --- a/zh/megatron-training.md +++ b/zh/megatron-training.md @@ -9,10 +9,8 @@ translators: proofreader: true --- -

如何使用 Megatron-LM 训练语言模型

+# 如何使用 Megatron-LM 训练语言模型 - - 在 PyTorch 中训练大语言模型不仅仅是写一个训练循环这么简单。我们通常需要将模型分布在多个设备上，并使用许多优化技术以实现稳定高效的训练。Hugging Face 🤗 [Accelerate](https://huggingface.co/docs/accelerate/index) 的创建是为了支持跨 GPU 和 TPU 的分布式训练，并使其能够非常容易的集成到训练代码中。🤗 [Transformers](https://huggingface.co/docs/transformers/index) 还支持使用 [Trainer](https://huggingface.co/docs/transformers/main_classes/trainer#transformers.Trainer) API 来训练，其在 PyTorch 中提供功能完整的训练接口，甚至不需要自己编写训练的代码。 diff --git a/zh/ml-for-games-1.md b/zh/ml-for-games-1.md index aa21be7d86..d1739f8253 100644 --- a/zh/ml-for-games-1.md +++ b/zh/ml-for-games-1.md @@ -11,8 +11,6 @@ translators: # 基于AI进行游戏开发：5天！创建一个农场游戏！第1部分 - - **欢迎使用 AI 进行游戏开发！** 在本系列中，我们将使用各种 AI 工具，在 5 天内创建一个功能完备的农场游戏。到本系列结束时，你将了解到如何将多种 AI 工具整合到游戏开发流程中。本系列文章将向你展示如何将 AI 工具用于： diff --git a/zh/ml-for-games-2.md b/zh/ml-for-games-2.md index ad44169488..02279d9923 100644 --- a/zh/ml-for-games-2.md +++ b/zh/ml-for-games-2.md @@ -11,8 +11,6 @@ translators: # 使用 ChatGPT 启发游戏创意｜基于 AI 5 天创建一个农场游戏，第 2 天 - - **欢迎使用 AI 进行游戏开发！** 在本系列中，我们将使用 AI 工具在 5 天内创建一个功能完备的农场游戏。到本系列结束时，您将了解到如何将多种 AI 工具整合到游戏开发流程中。本文将向您展示如何将 AI 工具用于: diff --git a/zh/ml-for-games-3.md b/zh/ml-for-games-3.md index f90aae931a..93597f5bc0 100644 --- a/zh/ml-for-games-3.md +++ b/zh/ml-for-games-3.md @@ -9,10 +9,8 @@ translators: proofreader: true --- -

AI 制作 3D 素材｜基于 AI 5 天创建一个农场游戏，第 3 天

+# AI 制作 3D 素材｜基于 AI 5 天创建一个农场游戏，第 3 天 - - **欢迎使用 AI 进行游戏开发**！在本系列中，我们将使用 AI 工具在 5 天内创建一个功能完备的农场游戏。到本系列结束时，您将了解到如何将多种 AI 工具整合到游戏开发流程中。本文将向您展示如何将 AI 工具用于: diff --git a/zh/ml-for-games-4.md b/zh/ml-for-games-4.md index 030b732962..35454bc424 100644 --- a/zh/ml-for-games-4.md +++ b/zh/ml-for-games-4.md @@ -9,10 +9,8 @@ translators: proofreader: true --- -

制作 2D 素材｜基于 AI 5 天创建一个农场游戏，第 4 天

+# 制作 2D 素材｜基于 AI 5 天创建一个农场游戏，第 4 天 - - **欢迎使用 AI 进行游戏开发！** 在本系列中，我们将使用 AI 工具在 5 天内创建一个功能完备的农场游戏。到本系列结束时，您将了解到如何将多种 AI 工具整合到游戏开发流程中。本系列文章将向您展示如何将 AI 工具用于: diff --git a/zh/ml-for-games-5.md b/zh/ml-for-games-5.md index 11650a0fb7..86ebf3864d 100644 --- a/zh/ml-for-games-5.md +++ b/zh/ml-for-games-5.md @@ -7,10 +7,8 @@ translators: - user: SuSung-boy --- -

ChatGPT 设计游戏剧情 | 基于 AI 5 天创建一个农场游戏，完结篇！

+# ChatGPT 设计游戏剧情 | 基于 AI 5 天创建一个农场游戏，完结篇！ - - **欢迎使用 AI 进行游戏开发！** 在本系列中，我们将使用 AI 工具在 5 天内创建一个功能完备的农场游戏。到本系列结束时，您将了解到如何将多种 AI 工具整合到游戏开发流程中。本文将向您展示如何将 AI 工具用于: diff --git a/zh/mms_adapters.md b/zh/mms_adapters.md index c44cdb479d..5872b56bd7 100644 --- a/zh/mms_adapters.md +++ b/zh/mms_adapters.md @@ -11,8 +11,6 @@ translators: # **微调用于多语言 ASR 的 MMS 适配器模型** - - Open In Colab diff --git a/zh/optimizing-bark.md b/zh/optimizing-bark.md index 640dcfe5cc..435debfce5 100644 --- a/zh/optimizing-bark.md +++ b/zh/optimizing-bark.md @@ -11,8 +11,6 @@ translators: # 使用 🤗 Transformers 优化文本转语音模型 Bark - - diff --git a/zh/optimum-onnxruntime-training.md b/zh/optimum-onnxruntime-training.md index c2038853d5..ccd8b0b79f 100644 --- a/zh/optimum-onnxruntime-training.md +++ b/zh/optimum-onnxruntime-training.md @@ -17,8 +17,6 @@ translators: # Optimum + ONNX Runtime: 更容易、更快地训练你的 Hugging Face 模型 - - ## 介绍 diff --git a/zh/os-llms.md b/zh/os-llms.md index f5284d0ef3..df086edd6f 100644 --- a/zh/os-llms.md +++ b/zh/os-llms.md @@ -9,10 +9,8 @@ translators: proofreader: true --- -

Hugging Face 的文本生成和大语言模型的开源生态

+# Hugging Face 的文本生成和大语言模型的开源生态 - - [更新于 2023 年 7 月 23 日: 添加 Llama 2。] diff --git a/zh/password-git-deprecation.md b/zh/password-git-deprecation.md index a78bb88a3c..53e9169b73 100644 --- a/zh/password-git-deprecation.md +++ b/zh/password-git-deprecation.md @@ -11,8 +11,6 @@ translators: # Hugging Face Hub: Git 操作认证的重要变更 - - 在 Hugging Face，我们一直致力于提升服务安全性，因此，我们将对通过 Git 与 Hugging Face Hub 交互时的认证方式进行更改。从 **2023 年 10 月 1 日** 开始，我们将不再接受密码作为命令行 Git 操作的认证方式。我们推荐使用更安全的认证方法，例如用个人访问令牌替换密码或使用 SSH 密钥。 diff --git a/zh/peft.md b/zh/peft.md index 39655a697a..59d1890338 100644 --- a/zh/peft.md +++ b/zh/peft.md @@ -8,8 +8,6 @@ authors: ## 🤗 PEFT：在低资源硬件上对十亿规模模型进行参数高效微调 - - ## 动机 diff --git a/zh/pytorch-ddp-accelerate-transformers.md b/zh/pytorch-ddp-accelerate-transformers.md index bf142de961..6e9ee7cbb7 100644 --- a/zh/pytorch-ddp-accelerate-transformers.md +++ b/zh/pytorch-ddp-accelerate-transformers.md @@ -11,8 +11,6 @@ translators: # 从 PyTorch DDP 到 Accelerate 到 Trainer，轻松掌握分布式训练 - - ## 概述 diff --git a/zh/red-teaming.md b/zh/red-teaming.md index 67704aba13..2d671261bd 100644 --- a/zh/red-teaming.md +++ b/zh/red-teaming.md @@ -13,8 +13,6 @@ translators: # 为大语言模型建立红队对抗 - - 在巨量文本数据下训练的大语言模型非常擅长生成现实文本。但是，这些模型通常会显现出一些不良行为像泄露个人信息 (比如社会保险号) 和生成错误信息，偏置，仇恨或有毒内容。举个例子，众所周知，GPT3 的早期版本就表现出性别歧视 (如下图) 与 [仇恨穆斯林言论](https://dl.acm.org/doi/abs/10.1145/3461702.3462624) 的情况。 diff --git a/zh/rlhf.md b/zh/rlhf.md index 6f5f7a11cb..1069b82ddc 100644 --- a/zh/rlhf.md +++ b/zh/rlhf.md @@ -16,8 +16,6 @@ translators: # ChatGPT 背后的“功臣”——RLHF 技术详解 - - OpenAI 推出的 ChatGPT 对话模型掀起了新的 AI 热潮，它面对多种多样的问题对答如流，似乎已经打破了机器和人的边界。这一工作的背后是大型语言模型 (Large Language Model，LLM) 生成领域的新训练范式：RLHF (Reinforcement Learning from Human Feedback) ，即以强化学习方式依据人类反馈优化语言模型。 diff --git a/zh/rwkv.md b/zh/rwkv.md index b796d6fdf0..bb521f1f9b 100644 --- a/zh/rwkv.md +++ b/zh/rwkv.md @@ -14,8 +14,6 @@ translators: # RWKV – transformer 与 RNN 的强强联合 - - 在 NLP (Natural Language Processing, 自然语言处理) 领域，ChatGPT 和其他的聊天机器人应用引起了极大的关注。每个社区为构建自己的应用，也都在持续地寻求强大、可靠的开源模型。自 Vaswani 等人于 2017 年首次提出 [Attention Is All You Need](https://arxiv.org/abs/1706.03762) 之后，基于 transformer 的强大的模型一直在不断地涌现，它们在 NLP 相关任务上的表现远远超过基于 RNN (Recurrent Neural Networks, 递归神经网络) 的 SoTA 模型，甚至多数认为 RNN 已死。而本文将介绍一个集 RNN 和 transformer 两者的优势于一身的全新网络架构 –RWKV！现已在 HuggingFace [transformers](https://github.com/huggingface/transformers) 库中支持。 diff --git a/zh/safecoder.md b/zh/safecoder.md index a4af709500..14e4fe7f66 100644 --- a/zh/safecoder.md +++ b/zh/safecoder.md @@ -10,8 +10,6 @@ translators: # 推介 SafeCoder - - 今天，我们向大家隆重介绍 SafeCoder —— 一款专为企业打造的代码助手解决方案。 diff --git a/zh/sd_distillation.md b/zh/sd_distillation.md index 02ae33c60f..b0b4f33a9d 100644 --- a/zh/sd_distillation.md +++ b/zh/sd_distillation.md @@ -14,10 +14,8 @@ translators: proofreader: true --- -

开源 SD-Small 和 SD-Tiny 知识蒸馏代码与权重

+# 开源 SD-Small 和 SD-Tiny 知识蒸馏代码与权重 - -

diff --git a/zh/setfit.md b/zh/setfit.md index f235ca06c5..bcf1162174 100644 --- a/zh/setfit.md +++ b/zh/setfit.md @@ -14,10 +14,8 @@ translators: proofreader: true --- -

SetFit: 高效的无提示少样本学习

+# SetFit: 高效的无提示少样本学习 - -

diff --git a/zh/speecht5.md b/zh/speecht5.md index 0ff485a1d4..f92a4ec3e2 100644 --- a/zh/speecht5.md +++ b/zh/speecht5.md @@ -9,8 +9,6 @@ translators: # 使用 SpeechT5 进行语音合成、识别和更多功能 - - 我们很高兴地宣布，SpeechT5 现在可用于 🤗 Transformers (一个开源库，提供最前沿的机器学习模型实现的开源库)。 diff --git a/zh/stable-diffusion-finetuning-intel.md b/zh/stable-diffusion-finetuning-intel.md index e089b7f86f..a1a0996cd9 100644 --- a/zh/stable-diffusion-finetuning-intel.md +++ b/zh/stable-diffusion-finetuning-intel.md @@ -11,8 +11,6 @@ translators: # 在英特尔 CPU 上微调 Stable Diffusion 模型 - - 扩散模型能够根据文本提示生成逼真的图像，这种能力促进了生成式人工智能的普及。人们已经开始把这些模型用在包括数据合成及内容创建在内的多个应用领域。 Hugging Face Hub 包含超过 5 千个预训练的文生图 [模型](https://huggingface.co/models?pipeline_tag=text-to-image&sort=trending)。这些模型与 [Diffusers 库](https://huggingface.co/docs/diffusers/index) 结合使用，使得构建图像生成工作流或者对不同的图像生成工作流进行实验变得无比简单。 diff --git a/zh/stable-diffusion-inference-intel.md b/zh/stable-diffusion-inference-intel.md index aeb5f4d4b7..49154dfff6 100644 --- a/zh/stable-diffusion-inference-intel.md +++ b/zh/stable-diffusion-inference-intel.md @@ -10,8 +10,6 @@ translators: # 在英特尔 CPU 上加速 Stable Diffusion 推理 - - 前一段时间，我们向大家介绍了最新一代的 [英特尔至强](https://www.intel.com/content/www/us/en/products/details/processors/xeon/scalable.html) CPU（代号 Sapphire Rapids），包括其用于加速深度学习的新硬件特性，以及如何使用它们来加速自然语言 transformer 模型的[分布式微调](https://huggingface.co/blog/intel-sapphire-rapids)和[推理](https://huggingface.co/blog/intel-sapphire-rapids-inference)。 diff --git a/zh/stackllama.md b/zh/stackllama.md index 5f850fc186..a0e229775b 100644 --- a/zh/stackllama.md +++ b/zh/stackllama.md @@ -16,8 +16,6 @@ translators: # “StackLLaMA”: 用 RLHF 训练 LLaMA 的手把手教程 - - 如 [ChatGPT](https://openai.com/blog/chatgpt)，[GPT-4](https://openai.com/research/gpt-4)，[Claude](https://www.anthropic.com/index/introducing-claude)语言模型 之强大，因为它们采用了 **基于人类反馈的强化学习** (Reinforcement Learning from Human Feedback, RLHF) 来使之更符合我们的使用场景。 diff --git a/zh/starchat-alpha.md b/zh/starchat-alpha.md index b890ae04f8..fe586068aa 100644 --- a/zh/starchat-alpha.md +++ b/zh/starchat-alpha.md @@ -19,8 +19,6 @@ translators: # 使用 StarCoder 创建一个编程助手 - - 如果你是一个软件开发者，你可能已经使用过 ChatGPT 或 GitHub 的 Copilot 去解决一些写代码过程中遇到的问题，比如将代码从一种语言翻译到另一种语言，或者通过自然语言，诸如“_写一个计算斐波那契数列第 N 个元素的 Python 程序_”，来自动生成代码。尽管这些专有系统功能强大，但它们仍然有很多不足，比如对训练所使用的公共数据透明度的缺失、没有能力去让它们适配自己的使用领域或代码库。 diff --git a/zh/starcoder.md b/zh/starcoder.md index 202fbf7f20..17261d4cea 100644 --- a/zh/starcoder.md +++ b/zh/starcoder.md @@ -12,8 +12,6 @@ translators: # StarCoder: 最先进的代码大模型 - - ## 关于 BigCode diff --git a/zh/t2i-sdxl-adapters.md b/zh/t2i-sdxl-adapters.md index 6ca8cd150b..26a9f3c190 100644 --- a/zh/t2i-sdxl-adapters.md +++ b/zh/t2i-sdxl-adapters.md @@ -17,8 +17,6 @@ translators: # 在 SDXL 上用 T2I-Adapter 实现高效可控的文生图 - -

diff --git a/zh/text-to-video.md b/zh/text-to-video.md index c341ffd4d0..42d399f826 100644 --- a/zh/text-to-video.md +++ b/zh/text-to-video.md @@ -9,10 +9,8 @@ translators: proofreader: true --- -

文生视频: 任务、挑战及现状

+# 文生视频: 任务、挑战及现状 - -

video-samples
diff --git a/zh/time-series-transformers.md b/zh/time-series-transformers.md index e96dbb6070..d83f39de83 100644 --- a/zh/time-series-transformers.md +++ b/zh/time-series-transformers.md @@ -8,10 +8,8 @@ translators: - user: zhongdongy --- -

使用 🤗 Transformers 进行概率时间序列预测

+# 使用 🤗 Transformers 进行概率时间序列预测 - - diff --git a/zh/train-your-controlnet.md b/zh/train-your-controlnet.md index 045d564946..7b182de2a9 100644 --- a/zh/train-your-controlnet.md +++ b/zh/train-your-controlnet.md @@ -12,8 +12,6 @@ translators: # 使用 diffusers 训练你自己的 ControlNet 🧨 - - ## 简介 [ControlNet](https://huggingface.co/blog/controlnet) 这个神经网络模型使得用户可以通过施加额外条件，细粒度地控制扩散模型的生成过程。这一技术最初由 [Adding Conditional Control to Text-to-Image Diffusion Models](https://huggingface.co/papers/2302.05543) 这篇论文提出，并很快地风靡了扩散模型的开源社区。作者开源了 8 个不同的模型，使得用户可以用 8 种条件去控制 Stable Diffusion 模型（包括版本 1 到 5 ）。这 8 种条件包括姿态估计、深度图、边缘图、素描图 [等等](https://huggingface.co/lllyasviel)。 diff --git a/zh/transformers-design-philosophy.md b/zh/transformers-design-philosophy.md index d94d53b561..aec3bf655f 100644 --- a/zh/transformers-design-philosophy.md +++ b/zh/transformers-design-philosophy.md @@ -9,13 +9,9 @@ translators: proofreader: true --- -

- 不要 重复自己* -

如何为现代机器学习设计开源库
- +# ~~不要~~ 重复自己* - - +##### *如何为现代机器学习设计开源库* ## 🤗 Transformers 设计理念 diff --git a/zh/trl-peft.md b/zh/trl-peft.md index 63f7fa2c53..36ee09af21 100644 --- a/zh/trl-peft.md +++ b/zh/trl-peft.md @@ -16,8 +16,6 @@ translators: # 在一张 24 GB 的消费级显卡上用 RLHF 微调 20B LLMs - - 我们很高兴正式发布 `trl` 与 `peft` 的集成，使任何人都可以更轻松地使用强化学习进行大型语言模型 (LLM) 微调！在这篇文章中，我们解释了为什么这是现有微调方法的有竞争力的替代方案。 diff --git a/zh/unity-api.md b/zh/unity-api.md index 18d34af5c1..f4e6b40392 100644 --- a/zh/unity-api.md +++ b/zh/unity-api.md @@ -9,10 +9,8 @@ translators: proofreader: true --- -

如何安装和使用 Hugging Face Unity API

+# 如何安装和使用 Hugging Face Unity API - - [Hugging Face Unity API](https://github.com/huggingface/unity-api) 提供了一个简单易用的接口，允许开发者在自己的 Unity 项目中方便地访问和使用 Hugging Face AI 模型，已集成到 [Hugging Face Inference API](https://huggingface.co/inference-api) 中。本文将详细介绍 API 的安装步骤和使用方法。 diff --git a/zh/unity-asr.md b/zh/unity-asr.md index fb5fdcd92c..2d65cd2221 100644 --- a/zh/unity-asr.md +++ b/zh/unity-asr.md @@ -9,10 +9,8 @@ translators: proofreader: true --- -

如何在 Unity 游戏中集成 AI 语音识别？

+# 如何在 Unity 游戏中集成 AI 语音识别？ - - ![Open Source AI Game Jam](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/124_ml-for-games/gamejambanner.png) [](https://itch.io/jam/open-source-ai-game-jam) diff --git a/zh/unity-in-spaces.md b/zh/unity-in-spaces.md index c9550a6cbb..da3f3f2761 100644 --- a/zh/unity-in-spaces.md +++ b/zh/unity-in-spaces.md @@ -11,8 +11,6 @@ translators: # 如何在 🤗 Space 上托管 Unity 游戏 - - 你知道吗？Hugging Face Space 可以托管自己开发的 Unity 游戏！惊不惊喜，意不意外？来了解一下吧！ diff --git a/zh/vision_language_pretraining.md b/zh/vision_language_pretraining.md index 96a4faaacd..e7ed3b8e32 100644 --- a/zh/vision_language_pretraining.md +++ b/zh/vision_language_pretraining.md @@ -10,8 +10,6 @@ translators: # 深入了解视觉语言模型 - - 人类学习本质上是多模态 (multi-modal) 的，因为联合利用多种感官有助于我们更好地理解和分析新信息。理所当然地，多模态学习的最新进展即是从这一人类学习过程的有效性中汲取灵感，创建可以利用图像、视频、文本、音频、肢体语言、面部表情和生理信号等各种模态信息来处理和链接信息的模型。 diff --git a/zh/vit-align.md b/zh/vit-align.md index 48d81c5794..4491c15834 100644 --- a/zh/vit-align.md +++ b/zh/vit-align.md @@ -13,8 +13,6 @@ translators: # Kakao Brain 的开源 ViT、ALIGN 和 COYO 文字 - - 最近 Kakao Brain 在 Hugging Face 发布了一个全新的开源图像文本数据集 [COYO](https://github.com/kakaobrain/coyo-dataset)，包含 7 亿对图像和文本，并训练了两个新的视觉语言模型 [ViT](https://github.com/kakaobrain/coyo-vit) 和 [ALIGN](https://github.com/kakaobrain/coyo-align)。