corpus.blog
41554 blogs · [ { "id": "01a07d5d-72e8-7140-82cd-cd927777f518", "title": "Transformers.js v3: WebGPU Support, New Models & Tasks, and More…", "url": "https://huggingface.co/blog/transformersjs-v3", "published_at": "2024-10-22T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9277c04099", "title": "Diffusers welcomes Stable Diffusion 3.5 Large", "url": "https://huggingface.co/blog/sd3-5", "published_at": "2024-10-22T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9278295f43", "title": "Releasing Outlines-core 0.1.0: structured generation in Rust and Python", "url": "https://huggingface.co/blog/outlines-core", "published_at": "2024-10-22T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927852a5b4", "title": "Deploying Speech-to-Speech on Hugging Face", "url": "https://huggingface.co/blog/s2s_endpoint", "published_at": "2024-10-22T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9278871438", "title": "“Llama 3.2 in Keras”", "url": "https://huggingface.co/blog/keras-llama-32", "published_at": "2024-10-21T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92795296c6", "title": "Fixing Gradient Accumulation", "url": "https://huggingface.co/blog/gradient_accumulation", "published_at": "2024-10-16T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9279eb65b7", "title": "Introducing the AMD 5th Gen EPYC™ CPU", "url": "https://huggingface.co/blog/huggingface-amd-turin", "published_at": "2024-10-10T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927a225b86", "title": "A Security Review of Gradio 5", "url": "https://huggingface.co/blog/gradio-5-security", "published_at": "2024-10-10T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927ac5218e", "title": "Welcome, Gradio 5", "url": "https://huggingface.co/blog/gradio-5", "published_at": "2024-10-09T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927acc40f5", "title": "Scaling AI-based Data Processing with Hugging Face + Dask", "url": "https://huggingface.co/blog/dask-scaling", "published_at": "2024-10-09T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927bc1bfaa", "title": "Faster Assisted Generation with Dynamic Speculation", "url": "https://huggingface.co/blog/dynamic_speculation_lookahead", "published_at": "2024-10-08T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927c060c30", "title": "Improving Parquet Dedupe on Hugging Face Hub", "url": "https://huggingface.co/blog/improve_parquet_dedupe", "published_at": "2024-10-05T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927c0fb7e1", "title": "Introducing the Open FinLLM Leaderboard", "url": "https://huggingface.co/blog/leaderboard-finbench", "published_at": "2024-10-04T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927c13fb74", "title": "A Short Summary of Chinese AI Global Expansion", "url": "https://huggingface.co/blog/chinese-ai-expansion", "published_at": "2024-10-03T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927c34dbb4", "title": "🇨🇿 BenCzechMark - Can your LLM Understand Czech?", "url": "https://huggingface.co/blog/benczechmark", "published_at": "2024-10-01T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927c4238cc", "title": "Converting Vertex-Colored Meshes to Textured Meshes", "url": "https://huggingface.co/blog/vertex-colored-to-textured-mesh", "published_at": "2024-09-30T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927d2cd3a0", "title": "Llama can now see and run on your device - welcome Llama 3.2", "url": "https://huggingface.co/blog/llama32", "published_at": "2024-09-25T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927d46fd8e", "title": "FineVideo: behind the scenes", "url": "https://huggingface.co/blog/fine-video", "published_at": "2024-09-23T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927d955226", "title": "Exploring the Daily Papers Page on Hugging Face", "url": "https://huggingface.co/blog/daily-papers", "published_at": "2024-09-23T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927e682951", "title": "Optimize and deploy with Optimum-Intel and OpenVINO GenAI", "url": "https://huggingface.co/blog/deploy-with-openvino", "published_at": "2024-09-20T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927e7480f5", "title": "Fine-tuning LLMs to 1.58bit: extreme quantization made easy", "url": "https://huggingface.co/blog/1_58_llm_extreme_quantization", "published_at": "2024-09-18T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927f0232da", "title": "Introducing the SQL Console on Datasets", "url": "https://huggingface.co/blog/sql-console", "published_at": "2024-09-17T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927fdb7622", "title": "Introducing Community Tools on HuggingChat", "url": "https://huggingface.co/blog/community-tools", "published_at": "2024-09-16T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9280827ed2", "title": "Accelerate 1.0.0", "url": "https://huggingface.co/blog/accelerate-v1", "published_at": "2024-09-13T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9280f70256", "title": "Hugging Face partners with TruffleHog to Scan for Secrets", "url": "https://huggingface.co/blog/trufflesecurity-partnership", "published_at": "2024-09-04T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9281b7521e", "title": "Scaling robotics datasets with video encoding", "url": "https://huggingface.co/blog/video-encoding", "published_at": "2024-08-27T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9281b928cd", "title": "The 5 Most Under-Rated Tools on Hugging Face", "url": "https://huggingface.co/blog/unsung-heroes", "published_at": "2024-08-22T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92829099fd", "title": "Improving Hugging Face Training Efficiency Through Packing with Flash Attention 2", "url": "https://huggingface.co/blog/packing-with-FA2", "published_at": "2024-08-21T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9282d79956", "title": "Deploy Meta Llama 3.1 405B on Google Cloud Vertex AI", "url": "https://huggingface.co/blog/llama31-on-vertex-ai", "published_at": "2024-08-19T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9283778a87", "title": "A failed experiment: Infini-Attention, and why we should keep trying?", "url": "https://huggingface.co/blog/infini-attention", "published_at": "2024-08-14T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9283da39a9", "title": "Introduction to ggml", "url": "https://huggingface.co/blog/introduction-to-ggml", "published_at": "2024-08-13T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9284a30660", "title": "Welcome Falcon Mamba: The first strong attention-free 7B model", "url": "https://huggingface.co/blog/falconmamba", "published_at": "2024-08-12T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd928500d7b2", "title": "Tool Use, Unified", "url": "https://huggingface.co/blog/unified-tool-use", "published_at": "2024-08-12T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92853fa5aa", "title": "XetHub is joining Hugging Face!", "url": "https://huggingface.co/blog/xethub-joins-hf", "published_at": "2024-08-08T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9286311241", "title": "2024 Security Feature Highlights", "url": "https://huggingface.co/blog/2024-security-features", "published_at": "2024-08-06T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92869681d3", "title": "Introducing TextImage Augmentation for Document Images", "url": "https://huggingface.co/blog/doc_aug_hf_alb", "published_at": "2024-08-06T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92874ccfe9", "title": "Google releases Gemma 2 2B, ShieldGemma and Gemma Scope", "url": "https://huggingface.co/blog/gemma-july-update", "published_at": "2024-07-31T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd928817a21c", "title": "Memory-efficient Diffusion Transformers with Quanto and Diffusers", "url": "https://huggingface.co/blog/quanto-diffusers", "published_at": "2024-07-30T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9288b3e132", "title": "Serverless Inference with Hugging Face and NVIDIA NIM", "url": "https://huggingface.co/blog/inference-dgx-cloud", "published_at": "2024-07-29T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92893d9483", "title": "LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?", "url": "https://huggingface.co/blog/zero-shot-vqa-docmatix", "published_at": "2024-07-25T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9289968bc4", "title": "Llama 3.1 - 405B, 70B & 8B with multilinguality and long context", "url": "https://huggingface.co/blog/llama31", "published_at": "2024-07-23T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9289e88e04", "title": "WWDC 24: Running Mistral 7B with Core ML", "url": "https://huggingface.co/blog/mistral-coreml", "published_at": "2024-07-22T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd928a7fb6d9", "title": "Docmatix - a huge dataset for Document Visual Question Answering", "url": "https://huggingface.co/blog/docmatix", "published_at": "2024-07-18T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd928b223253", "title": "TGI Multi-LoRA: Deploy Once, Serve 30 Models", "url": "https://huggingface.co/blog/multi-lora-serving", "published_at": "2024-07-18T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd928b904f02", "title": "SmolLM - blazingly fast and remarkably powerful", "url": "https://huggingface.co/blog/smollm", "published_at": "2024-07-16T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd928bf96198", "title": "How we leveraged distilabel to create an Argilla 2.0 Chatbot", "url": "https://huggingface.co/blog/argilla-chatbot", "published_at": "2024-07-16T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd928ccb1c30", "title": "How NuminaMath Won the 1st AIMO Progress Prize", "url": "https://huggingface.co/blog/winning-aimo-progress-prize", "published_at": "2024-07-11T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428059e6b902", "title": "Announcing New Hugging Face and KerasHub integration", "url": "https://huggingface.co/blog/keras-hub-integration", "published_at": "2024-07-10T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42805a241891", "title": "Experimenting with Automatic PII Detection on the Hub using Presidio", "url": "https://huggingface.co/blog/presidio-pii-detection", "published_at": "2024-07-10T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42805a739a68", "title": "Preference Optimization for Vision Language Models", "url": "https://huggingface.co/blog/dpo_vlm", "published_at": "2024-07-10T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42805ae2a05e", "title": "Google Cloud TPUs made available to Hugging Face users", "url": "https://huggingface.co/blog/tpu-inference-endpoints-spaces", "published_at": "2024-07-09T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42805b29c446", "title": "Banque des Territoires (CDC Group) x Polyconseil x Hugging Face: Enhancing a Major French Environmental Program with a Sovereign Data Solution", "url": "https://huggingface.co/blog/sovereign-data-solution-case-study", "published_at": "2024-07-09T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42805bcd28b9", "title": "Announcing New Dataset Search Features", "url": "https://huggingface.co/blog/datasets-filters", "published_at": "2024-07-08T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42805c09343a", "title": "Accelerating Protein Language Model ProtST on Intel Gaudi 2", "url": "https://huggingface.co/blog/intel-protein-language-model-protst", "published_at": "2024-07-03T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42805cf7d4af", "title": "Our Transformers Code Agent beats the GAIA benchmark 🏅", "url": "https://huggingface.co/blog/beating-gaia", "published_at": "2024-07-01T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42805d15e954", "title": "Welcome Gemma 2 - Google’s new open LLM", "url": "https://huggingface.co/blog/gemma2", "published_at": "2024-06-27T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42805d5aa6c5", "title": "XLSCOUT Unveils ParaEmbed 2.0: a Powerful Embedding Model Tailored for Patents and IP with Expert Support from Hugging Face", "url": "https://huggingface.co/blog/xlscout-case-study", "published_at": "2024-06-25T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42805dfabdaa", "title": "Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models", "url": "https://huggingface.co/blog/finetune-florence2", "published_at": "2024-06-24T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42805e956d44", "title": "Ethics and Society Newsletter #6: Building Better AI: The Importance of Data Quality", "url": "https://huggingface.co/blog/ethics-soc-6", "published_at": "2024-06-24T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42805f34e2f8", "title": "Data Is Better Together: A Look Back and Forward", "url": "https://huggingface.co/blog/dibt", "published_at": "2024-06-20T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42805f832499", "title": "Going multimodal: How Prezi is leveraging the Hub and the Expert Support Program to accelerate their ML roadmap", "url": "https://huggingface.co/blog/prezi-case-study", "published_at": "2024-06-19T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42805fc1788c", "title": "BigCodeBench: The Next Generation of HumanEval", "url": "https://huggingface.co/blog/leaderboard-bigcodebench", "published_at": "2024-06-18T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280609a0a37", "title": "From DeepSpeed to FSDP and Back Again with Hugging Face Accelerate", "url": "https://huggingface.co/blog/deepspeed-to-fsdp-and-back", "published_at": "2024-06-13T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428060e0ed78", "title": "Diffusers welcomes Stable Diffusion 3", "url": "https://huggingface.co/blog/sd3", "published_at": "2024-06-12T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428061a9b199", "title": "Putting RL back in RLHF", "url": "https://huggingface.co/blog/putting_rl_back_in_rlhf_with_rloo", "published_at": "2024-06-12T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428061ff16d2", "title": "Making sense of this mess", "url": "https://huggingface.co/blog/transformers-docs-redesign", "published_at": "2024-06-07T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428062a06c87", "title": "Introducing the Hugging Face Embedding Container for Amazon SageMaker", "url": "https://huggingface.co/blog/sagemaker-huggingface-embedding", "published_at": "2024-06-07T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42806306b3f6", "title": "Launching the Artificial Analysis Text to Image Leaderboard & Arena", "url": "https://huggingface.co/blog/leaderboard-artificial-analysis2", "published_at": "2024-06-06T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428063dacb44", "title": "Introducing NPC-Playground, a 3D playground to interact with LLM-powered NPCs", "url": "https://huggingface.co/blog/npc-gigax-cubzh", "published_at": "2024-06-05T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280644fb532", "title": "Faster assisted generation support for Intel Gaudi", "url": "https://huggingface.co/blog/assisted-generation-support-gaudi", "published_at": "2024-06-04T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428064e696d4", "title": "Space secrets security update", "url": "https://huggingface.co/blog/space-secrets-disclosure", "published_at": "2024-05-31T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280658e8cf2", "title": "Benchmarking Text Generation Inference", "url": "https://huggingface.co/blog/tgi-benchmarking", "published_at": "2024-05-29T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428065f13f89", "title": "Training and Finetuning Embedding Models with Sentence Transformers", "url": "https://huggingface.co/blog/train-sentence-transformers", "published_at": "2024-05-28T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280666a0dd8", "title": "Falcon 2: An 11B parameter pretrained language model and VLM, trained on over 5000B tokens and 11 languages", "url": "https://huggingface.co/blog/falcon2-11b", "published_at": "2024-05-24T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428067126fe4", "title": "CyberSecEval 2 - A Comprehensive Evaluation Framework for Cybersecurity Risks and Capabilities of Large Language Models", "url": "https://huggingface.co/blog/leaderboard-llamaguard", "published_at": "2024-05-24T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428067561c3a", "title": "Deploy models on AWS Inferentia2 from Hugging Face", "url": "https://huggingface.co/blog/inferentia-inference-endpoints", "published_at": "2024-05-22T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428067c0019b", "title": "Introducing Spaces Dev Mode for a seamless developer experience", "url": "https://huggingface.co/blog/spaces-dev-mode", "published_at": "2024-05-21T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428067c4452d", "title": "Build AI on premise with Dell Enterprise Hub", "url": "https://huggingface.co/blog/dell-enterprise-hub", "published_at": "2024-05-21T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280686c1c89", "title": "Hugging Face on AMD Instinct MI300 GPU", "url": "https://huggingface.co/blog/huggingface-amd-mi300", "published_at": "2024-05-21T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42806949b4ec", "title": "From cloud to developers: Hugging Face and Microsoft Deepen Collaboration", "url": "https://huggingface.co/blog/microsoft-collaboration", "published_at": "2024-05-21T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428069ad33da", "title": "Unlocking Longer Generation with Key-Value Cache Quantization", "url": "https://huggingface.co/blog/kv-cache-quantization", "published_at": "2024-05-16T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42806a6fb410", "title": "PaliGemma – Google's Cutting-Edge Open Vision Language Model", "url": "https://huggingface.co/blog/paligemma", "published_at": "2024-05-14T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42806a9b06b1", "title": "Hugging Face x LangChain : A new partner package", "url": "https://huggingface.co/blog/langchain", "published_at": "2024-05-14T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42806b4775f1", "title": "Introducing the Open Arabic LLM Leaderboard", "url": "https://huggingface.co/blog/leaderboard-arabic", "published_at": "2024-05-14T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42806b4fd477", "title": "License to Call: Introducing Transformers Agents 2.0", "url": "https://huggingface.co/blog/agents", "published_at": "2024-05-13T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42806b6a2e19", "title": "Subscribe to Enterprise Hub with your AWS Account", "url": "https://huggingface.co/blog/enterprise-hub-aws-marketplace", "published_at": "2024-05-09T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42806bcee38a", "title": "Building Cost-Efficient Enterprise RAG applications with Intel Gaudi 2 and Intel Xeon", "url": "https://huggingface.co/blog/cost-efficient-rag-applications-with-intel", "published_at": "2024-05-09T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42806c3c7e19", "title": "Introducing the Open Leaderboard for Hebrew LLMs!", "url": "https://huggingface.co/blog/leaderboard-hebrew", "published_at": "2024-05-05T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42806d1ff76a", "title": "Bringing the Artificial Analysis LLM Performance Leaderboard to Hugging Face", "url": "https://huggingface.co/blog/leaderboard-artificial-analysis", "published_at": "2024-05-03T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42806e10adfc", "title": "Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints", "url": "https://huggingface.co/blog/asr-diarization", "published_at": "2024-05-01T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42806e28d682", "title": "Improving Prompt Consistency with Structured Generations", "url": "https://huggingface.co/blog/evaluation-structured-outputs", "published_at": "2024-04-30T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42806e7fe2e8", "title": "StarCoder2-Instruct: Fully Transparent and Permissive Self-Alignment for Code Generation", "url": "https://huggingface.co/blog/sc2-instruct", "published_at": "2024-04-29T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42806f7bb455", "title": "Introducing the Open Chain of Thought Leaderboard", "url": "https://huggingface.co/blog/leaderboard-cot", "published_at": "2024-04-23T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42806fa53cf8", "title": "Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent", "url": "https://huggingface.co/blog/jat", "published_at": "2024-04-22T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428070444819", "title": "The Open Medical-LLM Leaderboard: Benchmarking Large Language Models in Healthcare", "url": "https://huggingface.co/blog/leaderboard-medicalllm", "published_at": "2024-04-19T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428070886eb0", "title": "Welcome Llama 3 - Meta's new open LLM", "url": "https://huggingface.co/blog/llama3", "published_at": "2024-04-18T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428070930e5b", "title": "AI Apps in a Flash with Gradio's Reload Mode", "url": "https://huggingface.co/blog/gradio-reload", "published_at": "2024-04-16T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428070b74d7d", "title": "Introducing the LiveCodeBench Leaderboard - Holistic and Contamination-Free Evaluation of Code LLMs", "url": "https://huggingface.co/blog/leaderboard-livecodebench", "published_at": "2024-04-16T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428070c31f76", "title": "Running Privacy-Preserving Inferences on Hugging Face Endpoints", "url": "https://huggingface.co/blog/fhe-endpoints", "published_at": "2024-04-16T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428071ae99d5", "title": "Ryght’s Journey to Empower Healthcare and Life Sciences with Expert Support from Hugging Face", "url": "https://huggingface.co/blog/ryght-case-study", "published_at": "2024-04-16T00:00:00+00:00" } ] posts Claim your blog
Back to Hugging Face
Blog · corpus.blog/blogs/huggingface.co/posts

Hugging Face

huggingface.co

2024

Transformers.js v3: WebGPU Support, New Models & Tasks, and More…original ↗
22 Oct 2024
Diffusers welcomes Stable Diffusion 3.5 Largeoriginal ↗
22 Oct 2024
Releasing Outlines-core 0.1.0: structured generation in Rust and Pythonoriginal ↗
22 Oct 2024
Deploying Speech-to-Speech on Hugging Faceoriginal ↗
22 Oct 2024
“Llama 3.2 in Keras”original ↗
21 Oct 2024
Fixing Gradient Accumulationoriginal ↗
16 Oct 2024
Introducing the AMD 5th Gen EPYC™ CPUoriginal ↗
10 Oct 2024
A Security Review of Gradio 5original ↗
10 Oct 2024
Welcome, Gradio 5original ↗
9 Oct 2024
Scaling AI-based Data Processing with Hugging Face + Daskoriginal ↗
9 Oct 2024
Faster Assisted Generation with Dynamic Speculationoriginal ↗
8 Oct 2024
Improving Parquet Dedupe on Hugging Face Huboriginal ↗
5 Oct 2024
Introducing the Open FinLLM Leaderboardoriginal ↗
4 Oct 2024
A Short Summary of Chinese AI Global Expansionoriginal ↗
3 Oct 2024
🇨🇿 BenCzechMark - Can your LLM Understand Czech?original ↗
1 Oct 2024
Converting Vertex-Colored Meshes to Textured Meshesoriginal ↗
30 Sept 2024
Llama can now see and run on your device - welcome Llama 3.2original ↗
25 Sept 2024
FineVideo: behind the scenesoriginal ↗
23 Sept 2024
Exploring the Daily Papers Page on Hugging Faceoriginal ↗
23 Sept 2024
Optimize and deploy with Optimum-Intel and OpenVINO GenAIoriginal ↗
20 Sept 2024
Fine-tuning LLMs to 1.58bit: extreme quantization made easyoriginal ↗
18 Sept 2024
Introducing the SQL Console on Datasetsoriginal ↗
17 Sept 2024
Introducing Community Tools on HuggingChatoriginal ↗
16 Sept 2024
Accelerate 1.0.0original ↗
13 Sept 2024
Hugging Face partners with TruffleHog to Scan for Secretsoriginal ↗
4 Sept 2024
Scaling robotics datasets with video encodingoriginal ↗
27 Aug 2024
The 5 Most Under-Rated Tools on Hugging Faceoriginal ↗
22 Aug 2024
Improving Hugging Face Training Efficiency Through Packing with Flash Attention 2original ↗
21 Aug 2024
Deploy Meta Llama 3.1 405B on Google Cloud Vertex AIoriginal ↗
19 Aug 2024
A failed experiment: Infini-Attention, and why we should keep trying?original ↗
14 Aug 2024
Introduction to ggmloriginal ↗
13 Aug 2024
Welcome Falcon Mamba: The first strong attention-free 7B modeloriginal ↗
12 Aug 2024
Tool Use, Unifiedoriginal ↗
12 Aug 2024
XetHub is joining Hugging Face!original ↗
8 Aug 2024
2024 Security Feature Highlightsoriginal ↗
6 Aug 2024
Introducing TextImage Augmentation for Document Imagesoriginal ↗
6 Aug 2024
Google releases Gemma 2 2B, ShieldGemma and Gemma Scopeoriginal ↗
31 Jul 2024
Memory-efficient Diffusion Transformers with Quanto and Diffusersoriginal ↗
30 Jul 2024
Serverless Inference with Hugging Face and NVIDIA NIMoriginal ↗
29 Jul 2024
LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?original ↗
25 Jul 2024
Llama 3.1 - 405B, 70B & 8B with multilinguality and long contextoriginal ↗
23 Jul 2024
WWDC 24: Running Mistral 7B with Core MLoriginal ↗
22 Jul 2024
Docmatix - a huge dataset for Document Visual Question Answeringoriginal ↗
18 Jul 2024
TGI Multi-LoRA: Deploy Once, Serve 30 Modelsoriginal ↗
18 Jul 2024
SmolLM - blazingly fast and remarkably powerfuloriginal ↗
16 Jul 2024
How we leveraged distilabel to create an Argilla 2.0 Chatbotoriginal ↗
16 Jul 2024
How NuminaMath Won the 1st AIMO Progress Prizeoriginal ↗
11 Jul 2024
Announcing New Hugging Face and KerasHub integrationoriginal ↗
10 Jul 2024
Experimenting with Automatic PII Detection on the Hub using Presidiooriginal ↗
10 Jul 2024
Preference Optimization for Vision Language Modelsoriginal ↗
10 Jul 2024
Google Cloud TPUs made available to Hugging Face usersoriginal ↗
9 Jul 2024
Banque des Territoires (CDC Group) x Polyconseil x Hugging Face: Enhancing a Major French Environmental Program with a Sovereign Data Solutionoriginal ↗
9 Jul 2024
Announcing New Dataset Search Featuresoriginal ↗
8 Jul 2024
Accelerating Protein Language Model ProtST on Intel Gaudi 2original ↗
3 Jul 2024
Our Transformers Code Agent beats the GAIA benchmark 🏅original ↗
1 Jul 2024
Welcome Gemma 2 - Google’s new open LLMoriginal ↗
27 Jun 2024
XLSCOUT Unveils ParaEmbed 2.0: a Powerful Embedding Model Tailored for Patents and IP with Expert Support from Hugging Faceoriginal ↗
25 Jun 2024
Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Modelsoriginal ↗
24 Jun 2024
Ethics and Society Newsletter #6: Building Better AI: The Importance of Data Qualityoriginal ↗
24 Jun 2024
Data Is Better Together: A Look Back and Forwardoriginal ↗
20 Jun 2024
Going multimodal: How Prezi is leveraging the Hub and the Expert Support Program to accelerate their ML roadmaporiginal ↗
19 Jun 2024
BigCodeBench: The Next Generation of HumanEvaloriginal ↗
18 Jun 2024
From DeepSpeed to FSDP and Back Again with Hugging Face Accelerateoriginal ↗
13 Jun 2024
Diffusers welcomes Stable Diffusion 3original ↗
12 Jun 2024
Putting RL back in RLHForiginal ↗
12 Jun 2024
Making sense of this messoriginal ↗
7 Jun 2024
Introducing the Hugging Face Embedding Container for Amazon SageMakeroriginal ↗
7 Jun 2024
Launching the Artificial Analysis Text to Image Leaderboard & Arenaoriginal ↗
6 Jun 2024
Introducing NPC-Playground, a 3D playground to interact with LLM-powered NPCsoriginal ↗
5 Jun 2024
Faster assisted generation support for Intel Gaudioriginal ↗
4 Jun 2024
Space secrets security updateoriginal ↗
31 May 2024
Benchmarking Text Generation Inferenceoriginal ↗
29 May 2024
Training and Finetuning Embedding Models with Sentence Transformersoriginal ↗
28 May 2024
Falcon 2: An 11B parameter pretrained language model and VLM, trained on over 5000B tokens and 11 languagesoriginal ↗
24 May 2024
CyberSecEval 2 - A Comprehensive Evaluation Framework for Cybersecurity Risks and Capabilities of Large Language Modelsoriginal ↗
24 May 2024
Deploy models on AWS Inferentia2 from Hugging Faceoriginal ↗
22 May 2024
Introducing Spaces Dev Mode for a seamless developer experienceoriginal ↗
21 May 2024
Build AI on premise with Dell Enterprise Huboriginal ↗
21 May 2024
Hugging Face on AMD Instinct MI300 GPUoriginal ↗
21 May 2024
From cloud to developers: Hugging Face and Microsoft Deepen Collaborationoriginal ↗
21 May 2024
Unlocking Longer Generation with Key-Value Cache Quantizationoriginal ↗
16 May 2024
PaliGemma – Google's Cutting-Edge Open Vision Language Modeloriginal ↗
14 May 2024
Hugging Face x LangChain : A new partner packageoriginal ↗
14 May 2024
Introducing the Open Arabic LLM Leaderboardoriginal ↗
14 May 2024
License to Call: Introducing Transformers Agents 2.0original ↗
13 May 2024
Subscribe to Enterprise Hub with your AWS Accountoriginal ↗
9 May 2024
Building Cost-Efficient Enterprise RAG applications with Intel Gaudi 2 and Intel Xeonoriginal ↗
9 May 2024
Introducing the Open Leaderboard for Hebrew LLMs!original ↗
5 May 2024
Bringing the Artificial Analysis LLM Performance Leaderboard to Hugging Faceoriginal ↗
3 May 2024
Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpointsoriginal ↗
1 May 2024
Improving Prompt Consistency with Structured Generationsoriginal ↗
30 Apr 2024
StarCoder2-Instruct: Fully Transparent and Permissive Self-Alignment for Code Generationoriginal ↗
29 Apr 2024
Introducing the Open Chain of Thought Leaderboardoriginal ↗
23 Apr 2024
Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agentoriginal ↗
22 Apr 2024
The Open Medical-LLM Leaderboard: Benchmarking Large Language Models in Healthcareoriginal ↗
19 Apr 2024
Welcome Llama 3 - Meta's new open LLMoriginal ↗
18 Apr 2024
AI Apps in a Flash with Gradio's Reload Modeoriginal ↗
16 Apr 2024
Introducing the LiveCodeBench Leaderboard - Holistic and Contamination-Free Evaluation of Code LLMsoriginal ↗
16 Apr 2024
Running Privacy-Preserving Inferences on Hugging Face Endpointsoriginal ↗
16 Apr 2024
Ryght’s Journey to Empower Healthcare and Life Sciences with Expert Support from Hugging Faceoriginal ↗
16 Apr 2024
Previous Next