corpus.blog
41554 blogs Β· [ { "id": "01a07d5d-72e8-7140-82cd-cd9249f5c615", "title": "Prefill and Decode for Concurrent Requests - Optimizing LLM Performance", "url": "https://huggingface.co/blog/tngtech/llm-performance-prefill-decode-concurrent-requests", "published_at": "2025-04-16T10:10:58+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924a2a5728", "title": "17 Reasons Why Gradio Isn't Just Another UI Library", "url": "https://huggingface.co/blog/why-gradio-stands-out", "published_at": "2025-04-16T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924a6dd09f", "title": "Cohere on Hugging Face Inference Providers πŸ”₯", "url": "https://huggingface.co/blog/inference-providers-cohere", "published_at": "2025-04-16T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924abf5a7c", "title": "Introducing HELMET: Holistically Evaluating Long-context Language Models", "url": "https://huggingface.co/blog/helmet", "published_at": "2025-04-16T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924bbc43c6", "title": "Hugging Face to sell open-source robots thanks to Pollen Robotics acquisition πŸ€–", "url": "https://huggingface.co/blog/hugging-face-pollen-robotics-acquisition", "published_at": "2025-04-14T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924c519935", "title": "4M Models Scanned: Protect AI + Hugging Face 6 Months In", "url": "https://huggingface.co/blog/pai-6-month", "published_at": "2025-04-14T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924cb65e9f", "title": "Visual Salamandra: Pushing the Boundaries of Multimodal Understanding", "url": "https://huggingface.co/blog/BSC-LT/visualsalamandra7b", "published_at": "2025-04-11T14:21:56+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924d547bbb", "title": "Hugging Face and Cloudflare Partner to Make Real-Time Speech and Video Seamless with FastRTC", "url": "https://huggingface.co/blog/fastrtc-cloudflare", "published_at": "2025-04-09T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924dac7f36", "title": "Arabic Leaderboards: Introducing Arabic Instruction Following, Updating AraGen, and More", "url": "https://huggingface.co/blog/leaderboard-3c3h-aragen-ifeval", "published_at": "2025-04-08T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924e198753", "title": "Welcome Llama 4 Maverick & Scout on Hugging Face", "url": "https://huggingface.co/blog/llama4-release", "published_at": "2025-04-05T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924ebbc9b7", "title": "Journey to 1 Million Gradio Users!", "url": "https://huggingface.co/blog/gradio-1m", "published_at": "2025-04-04T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924f0e0c3b", "title": "The NLP Course is becoming the LLM Course", "url": "https://huggingface.co/blog/llm-course", "published_at": "2025-04-03T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924f9f1007", "title": "Efficient Request Queueing – Optimizing LLM Performance", "url": "https://huggingface.co/blog/tngtech/llm-performance-request-queueing", "published_at": "2025-04-02T13:33:53+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9250565e77", "title": "How Hugging Face Scaled Secrets Management for AI Infrastructure", "url": "https://huggingface.co/blog/scaling-secrets-management", "published_at": "2025-03-31T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9250cb09f6", "title": "πŸš€ Accelerating LLM Inference with TGI on Intel Gaudi", "url": "https://huggingface.co/blog/intel-gaudi-backend-for-tgi", "published_at": "2025-03-28T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92510a1f8b", "title": "Open R1: Update #4", "url": "https://huggingface.co/blog/open-r1/update-4", "published_at": "2025-03-26T18:47:29+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9251abb3a8", "title": "Training and Finetuning Reranker Models with Sentence Transformers", "url": "https://huggingface.co/blog/train-reranker", "published_at": "2025-03-26T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92527afcc5", "title": "Introducing Gradio's new Dataframe!", "url": "https://huggingface.co/blog/gradio-dataframe-upgrade", "published_at": "2025-03-24T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925294b4ba", "title": "The New and Fresh analytics in Inference Endpoints", "url": "https://huggingface.co/blog/endpoint-analytics", "published_at": "2025-03-21T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9253089754", "title": "Open R1: How to use OlympicCoder locally for coding", "url": "https://huggingface.co/blog/olympic-coder-lmstudio", "published_at": "2025-03-20T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9253fed38e", "title": "AI Policy @πŸ€—: Response to the White House AI Action Plan RFI", "url": "https://huggingface.co/blog/ai-action-wh-2025", "published_at": "2025-03-19T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925423d95b", "title": "NVIDIA's GTC 2025 Announcement for Physical AI Developers: New Open Models and Datasets", "url": "https://huggingface.co/blog/nvidia-physical-ai", "published_at": "2025-03-18T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92548fe51b", "title": "Xet is on the Hub", "url": "https://huggingface.co/blog/xet-on-the-hub", "published_at": "2025-03-18T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92558160f7", "title": "Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM", "url": "https://huggingface.co/blog/gemma3", "published_at": "2025-03-12T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92558da5d1", "title": "Open R1: Update #3", "url": "https://huggingface.co/blog/open-r1/update-3", "published_at": "2025-03-11T20:40:47+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9255a757c2", "title": "LeRobot goes to driving school: World’s largest open-source self-driving dataset", "url": "https://huggingface.co/blog/lerobot-goes-to-driving-school", "published_at": "2025-03-11T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925646de4a", "title": "LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone!", "url": "https://huggingface.co/blog/llm-inference-on-edge", "published_at": "2025-03-07T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9256f7c6b1", "title": "Hugging Face and JFrog partner to make AI Security more transparent", "url": "https://huggingface.co/blog/jfrog", "published_at": "2025-03-04T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9257123c51", "title": "A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality", "url": "https://huggingface.co/blog/aya-vision", "published_at": "2025-03-04T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925750d17e", "title": "Trace & Evaluate your Agent with Arize Phoenix", "url": "https://huggingface.co/blog/smolagents-phoenix", "published_at": "2025-02-28T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925787fdfa", "title": "HuggingFace, IISc partner to supercharge model building on India's diverse languages", "url": "https://huggingface.co/blog/iisc-huggingface-collab", "published_at": "2025-02-27T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92587aba3c", "title": "FastRTC: The Real-Time Communication Library for Python", "url": "https://huggingface.co/blog/fastrtc", "published_at": "2025-02-25T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9258b82ccc", "title": "Remote VAEs for decoding with Inference Endpoints πŸ€—", "url": "https://huggingface.co/blog/remote_vae", "published_at": "2025-02-24T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92598b667f", "title": "SigLIP 2: A better multilingual vision language encoder", "url": "https://huggingface.co/blog/siglip2", "published_at": "2025-02-21T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92598d2723", "title": "SmolVLM2: Bringing Video Understanding to Every Device", "url": "https://huggingface.co/blog/smolvlm2", "published_at": "2025-02-20T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925a69489e", "title": "PaliGemma 2 Mix - New Instruction Vision Language Models by Google", "url": "https://huggingface.co/blog/paligemma2mix", "published_at": "2025-02-19T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925aeefa72", "title": "Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita πŸ”₯", "url": "https://huggingface.co/blog/inference-providers-nebius-novita-hyperbolic", "published_at": "2025-02-18T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925b2a8d76", "title": "Welcome Fireworks.ai on the Hub πŸŽ†", "url": "https://huggingface.co/blog/fireworks-ai", "published_at": "2025-02-14T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925b96d5e6", "title": "Fixing Open LLM Leaderboard with Math-Verify", "url": "https://huggingface.co/blog/math_verify_leaderboard", "published_at": "2025-02-14T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925c66d17d", "title": "1 Billion Classifications", "url": "https://huggingface.co/blog/billion-classifications", "published_at": "2025-02-13T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925d06d0f4", "title": "From Chunks to Blocks: Accelerating Uploads and Downloads on the Hub", "url": "https://huggingface.co/blog/from-chunks-to-blocks", "published_at": "2025-02-12T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925d09023d", "title": "Build awesome datasets for video generation", "url": "https://huggingface.co/blog/vid_ds_scripts", "published_at": "2025-02-12T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925d757cda", "title": "Open R1: Update #2", "url": "https://huggingface.co/blog/open-r1/update-2", "published_at": "2025-02-10T16:10:47+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925e451cbe", "title": "The Open Arabic LLM Leaderboard 2", "url": "https://huggingface.co/blog/leaderboard-arabic-v2", "published_at": "2025-02-10T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925f321e9d", "title": "Open-source DeepResearch – Freeing our search agents", "url": "https://huggingface.co/blog/open-deep-research", "published_at": "2025-02-04T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925f95ab37", "title": "Ο€0 and Ο€0-FAST: Vision-Language-Action Models for General Robot Control", "url": "https://huggingface.co/blog/pi0", "published_at": "2025-02-04T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd925f9ac74a", "title": "DABStep: Data Agent Benchmark for Multi-step Reasoning", "url": "https://huggingface.co/blog/dabstep", "published_at": "2025-02-04T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9260030618", "title": "Open-R1: Update #1", "url": "https://huggingface.co/blog/open-r1/update-1", "published_at": "2025-02-02T00:04:28+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9260b02760", "title": "Mini-R1: Reproduce Deepseek R1 β€žaha momentβ€œ a RL tutorial", "url": "https://huggingface.co/blog/open-r1/mini-r1-contdown-game", "published_at": "2025-01-31T10:29:40+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92610ca700", "title": "The AI tools for Art Newsletter - Issue 1", "url": "https://huggingface.co/blog/ai-art-newsletter-jan-25", "published_at": "2025-01-31T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92619d46d4", "title": "How to deploy and fine-tune DeepSeek models on AWS", "url": "https://huggingface.co/blog/deepseek-r1-aws", "published_at": "2025-01-30T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9261c31cae", "title": "Welcome to Inference Providers on the Hub πŸ”₯", "url": "https://huggingface.co/blog/inference-providers", "published_at": "2025-01-28T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9262066ff7", "title": "Open-R1: a fully open reproduction of DeepSeek-R1", "url": "https://huggingface.co/blog/open-r1", "published_at": "2025-01-28T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9262ade6cc", "title": "State of open video generation models in Diffusers", "url": "https://huggingface.co/blog/video_gen", "published_at": "2025-01-27T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92632743e1", "title": "We now support VLMs in smolagents!", "url": "https://huggingface.co/blog/smolagents-can-see", "published_at": "2025-01-24T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926391263d", "title": "Mastering Long Contexts in LLMs with KVPress", "url": "https://huggingface.co/blog/nvidia/kvpress", "published_at": "2025-01-23T08:03:03+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9263c93b1a", "title": "SmolVLM Grows Smaller – Introducing the 256M & 500M Models!", "url": "https://huggingface.co/blog/smolervlm", "published_at": "2025-01-23T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9264a95df5", "title": "Hugging Face and FriendliAI partner to supercharge model deployment on the Hub", "url": "https://huggingface.co/blog/friendliai-partnership", "published_at": "2025-01-22T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9265480764", "title": "Yay! Organizations can now publish blog Articles", "url": "https://huggingface.co/blog/huggingface/blog-articles-for-orgs", "published_at": "2025-01-20T18:58:24+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926581d189", "title": "Timm ❀️ Transformers: Use any timm model with transformers", "url": "https://huggingface.co/blog/timm-transformers", "published_at": "2025-01-16T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926596fb50", "title": "Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference", "url": "https://huggingface.co/blog/tgi-multi-backend", "published_at": "2025-01-16T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9265de55f7", "title": "Train 400x faster Static Embedding Models with Sentence Transformers", "url": "https://huggingface.co/blog/static-embeddings", "published_at": "2025-01-15T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92662b6ca4", "title": "AI Agents Are Here. What Now?", "url": "https://huggingface.co/blog/ethics-soc-7", "published_at": "2025-01-13T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926670e66b", "title": "Visual Document Retrieval Goes Multilingual", "url": "https://huggingface.co/blog/vdr-2b-multilingual", "published_at": "2025-01-10T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9267453fb7", "title": "COβ‚‚ Emissions and Models Performance: Insights from the Open LLM Leaderboard", "url": "https://huggingface.co/blog/leaderboard-emissions-analysis", "published_at": "2025-01-09T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926789ee1d", "title": "Introducing smolagents: simple agents that write actions in code.", "url": "https://huggingface.co/blog/smolagents", "published_at": "2024-12-31T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9267c6a032", "title": "Visualize and understand GPU memory in PyTorch", "url": "https://huggingface.co/blog/train_memory", "published_at": "2024-12-24T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92686ac021", "title": "Controlling Language Model Generation with NVIDIA's LogitsProcessorZoo", "url": "https://huggingface.co/blog/logits-processor-zoo", "published_at": "2024-12-23T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9269480aa3", "title": "Evaluating Audio Reasoning with Big Bench Audio", "url": "https://huggingface.co/blog/big-bench-audio-release", "published_at": "2024-12-20T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9269b35102", "title": "Finally, a Replacement for BERT: Introducing ModernBERT", "url": "https://huggingface.co/blog/modernbert", "published_at": "2024-12-19T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9269cf1429", "title": "Bamba: Inference-Efficient Hybrid Mamba2 Model", "url": "https://huggingface.co/blog/bamba", "published_at": "2024-12-18T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9269e54f4d", "title": "Welcome to the Falcon 3 Family of Open Models!", "url": "https://huggingface.co/blog/falcon3", "published_at": "2024-12-17T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926a77c093", "title": "Benchmarking Language Model Performance on 5th Gen Xeon at GCP", "url": "https://huggingface.co/blog/intel-gcp-c4", "published_at": "2024-12-17T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926a7abf8c", "title": "Introducing the Synthetic Data Generator - Build Datasets with Natural Language", "url": "https://huggingface.co/blog/synthetic-data-generator", "published_at": "2024-12-16T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926b0fe52f", "title": "LeMaterial: an open source initiative to accelerate materials discovery and research", "url": "https://huggingface.co/blog/lematerial", "published_at": "2024-12-10T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926be43701", "title": "Hugging Face models in Amazon Bedrock", "url": "https://huggingface.co/blog/bedrock-marketplace", "published_at": "2024-12-09T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926c240d59", "title": "Open Preference Dataset for Text-to-Image Generation by the πŸ€— Community", "url": "https://huggingface.co/blog/image-preferences", "published_at": "2024-12-09T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926c9af197", "title": "Welcome PaliGemma 2 – New vision language models by Google", "url": "https://huggingface.co/blog/paligemma2", "published_at": "2024-12-05T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926d78cf0b", "title": "How good are LLMs at fixing their mistakes? A chatbot arena experiment with Keras and TPUs", "url": "https://huggingface.co/blog/keras-chatbot-arena", "published_at": "2024-12-05T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926dc601fd", "title": "Rethinking LLM Evaluation with 3C3H: AraGen Benchmark and Leaderboard", "url": "https://huggingface.co/blog/leaderboard-3c3h-aragen", "published_at": "2024-12-04T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926e7ee358", "title": "Investing in Performance: Fine-tune small models with LLM insights - a CFM case study", "url": "https://huggingface.co/blog/cfm-case-study", "published_at": "2024-12-03T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926eb1e15f", "title": "Open Source Developers Guide to the EU AI Act", "url": "https://huggingface.co/blog/eu-ai-act-for-oss-developers", "published_at": "2024-12-02T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926eeb15d6", "title": "Rearchitecting Hugging Face Uploads and Downloads", "url": "https://huggingface.co/blog/rearchitecting-uploads-and-downloads", "published_at": "2024-11-26T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd926f39288c", "title": "SmolVLM - small yet mighty Vision Language Model", "url": "https://huggingface.co/blog/smolvlm", "published_at": "2024-11-26T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9270033fff", "title": "You could have designed state of the art positional encoding", "url": "https://huggingface.co/blog/designing-positional-encoding", "published_at": "2024-11-25T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9270182d8e", "title": "Letting Large Models Debate: The First Multilingual LLM Debate Competition", "url": "https://huggingface.co/blog/debate", "published_at": "2024-11-20T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92702a17ff", "title": "From Files to Chunks: Improving HF Storage Efficiency", "url": "https://huggingface.co/blog/from-files-to-chunks", "published_at": "2024-11-20T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927043cdfc", "title": "Faster Text Generation with Self-Speculative Decoding", "url": "https://huggingface.co/blog/layerskip", "published_at": "2024-11-20T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927121fca0", "title": "Introducing the Open Leaderboard for Japanese LLMs!", "url": "https://huggingface.co/blog/leaderboard-japanese", "published_at": "2024-11-20T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92720944a0", "title": "Judge Arena: Benchmarking LLMs as Evaluators", "url": "https://huggingface.co/blog/arena-atla", "published_at": "2024-11-19T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9272559c0a", "title": "Share your open ML datasets on Hugging Face Hub!", "url": "https://huggingface.co/blog/researcher-dataset-sharing", "published_at": "2024-11-12T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9272a55251", "title": "Hugging Face + PyCharm", "url": "https://huggingface.co/blog/pycharm-integration", "published_at": "2024-11-05T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927364b517", "title": "Argilla 2.4: Easily Build Fine-Tuning and Evaluation Datasets on the Hub β€” No Code Required", "url": "https://huggingface.co/blog/argilla-ui-hub", "published_at": "2024-11-04T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9273b34406", "title": "Universal Assisted Generation: Faster Decoding with Any Assistant Model", "url": "https://huggingface.co/blog/universal_assisted_generation", "published_at": "2024-10-29T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92745252fa", "title": "Expert Support case study: Bolstering a RAG app with LLM-as-a-Judge", "url": "https://huggingface.co/blog/digital-green-llm-judge", "published_at": "2024-10-28T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92746cdaf0", "title": "A Deepdive into Aya Expanse: Advancing the Frontier of Multilinguality", "url": "https://huggingface.co/blog/aya-expanse", "published_at": "2024-10-24T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9274a9107e", "title": "Introducing SynthID Text", "url": "https://huggingface.co/blog/synthid-text", "published_at": "2024-10-23T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927588e31b", "title": "Introducing HUGS - Scale your AI with Open Models", "url": "https://huggingface.co/blog/hugs", "published_at": "2024-10-23T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd927681056a", "title": "CinePile 2.0 - making stronger datasets with adversarial refinement", "url": "https://huggingface.co/blog/cinepile2", "published_at": "2024-10-23T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9277556228", "title": "Hugging Face Teams Up with Protect AI: Enhancing Model Security for the ML Community", "url": "https://huggingface.co/blog/protectai", "published_at": "2024-10-22T00:00:00+00:00" } ] posts Claim your blog
Back to Hugging Face
Blog Β· corpus.blog/blogs/huggingface.co/posts

Hugging Face

huggingface.co

2025

Prefill and Decode for Concurrent Requests - Optimizing LLM Performanceoriginal β†—
16 Apr 2025
17 Reasons Why Gradio Isn't Just Another UI Libraryoriginal β†—
16 Apr 2025
Cohere on Hugging Face Inference Providers πŸ”₯original β†—
16 Apr 2025
Introducing HELMET: Holistically Evaluating Long-context Language Modelsoriginal β†—
16 Apr 2025
Hugging Face to sell open-source robots thanks to Pollen Robotics acquisition πŸ€–original β†—
14 Apr 2025
4M Models Scanned: Protect AI + Hugging Face 6 Months Inoriginal β†—
14 Apr 2025
Visual Salamandra: Pushing the Boundaries of Multimodal Understandingoriginal β†—
11 Apr 2025
Hugging Face and Cloudflare Partner to Make Real-Time Speech and Video Seamless with FastRTCoriginal β†—
9 Apr 2025
Arabic Leaderboards: Introducing Arabic Instruction Following, Updating AraGen, and Moreoriginal β†—
8 Apr 2025
Welcome Llama 4 Maverick & Scout on Hugging Faceoriginal β†—
5 Apr 2025
Journey to 1 Million Gradio Users!original β†—
4 Apr 2025
The NLP Course is becoming the LLM Courseoriginal β†—
3 Apr 2025
Efficient Request Queueing – Optimizing LLM Performanceoriginal β†—
2 Apr 2025
How Hugging Face Scaled Secrets Management for AI Infrastructureoriginal β†—
31 Mar 2025
πŸš€ Accelerating LLM Inference with TGI on Intel Gaudioriginal β†—
28 Mar 2025
Open R1: Update #4original β†—
26 Mar 2025
Training and Finetuning Reranker Models with Sentence Transformersoriginal β†—
26 Mar 2025
Introducing Gradio's new Dataframe!original β†—
24 Mar 2025
The New and Fresh analytics in Inference Endpointsoriginal β†—
21 Mar 2025
Open R1: How to use OlympicCoder locally for codingoriginal β†—
20 Mar 2025
AI Policy @πŸ€—: Response to the White House AI Action Plan RFIoriginal β†—
19 Mar 2025
NVIDIA's GTC 2025 Announcement for Physical AI Developers: New Open Models and Datasetsoriginal β†—
18 Mar 2025
Xet is on the Huboriginal β†—
18 Mar 2025
Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLMoriginal β†—
12 Mar 2025
Open R1: Update #3original β†—
11 Mar 2025
LeRobot goes to driving school: World’s largest open-source self-driving datasetoriginal β†—
11 Mar 2025
LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone!original β†—
7 Mar 2025
Hugging Face and JFrog partner to make AI Security more transparentoriginal β†—
4 Mar 2025
A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodalityoriginal β†—
4 Mar 2025
Trace & Evaluate your Agent with Arize Phoenixoriginal β†—
28 Feb 2025
HuggingFace, IISc partner to supercharge model building on India's diverse languagesoriginal β†—
27 Feb 2025
FastRTC: The Real-Time Communication Library for Pythonoriginal β†—
25 Feb 2025
Remote VAEs for decoding with Inference Endpoints πŸ€—original β†—
24 Feb 2025
SigLIP 2: A better multilingual vision language encoderoriginal β†—
21 Feb 2025
SmolVLM2: Bringing Video Understanding to Every Deviceoriginal β†—
20 Feb 2025
PaliGemma 2 Mix - New Instruction Vision Language Models by Googleoriginal β†—
19 Feb 2025
Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita πŸ”₯original β†—
18 Feb 2025
Welcome Fireworks.ai on the Hub πŸŽ†original β†—
14 Feb 2025
Fixing Open LLM Leaderboard with Math-Verifyoriginal β†—
14 Feb 2025
1 Billion Classificationsoriginal β†—
13 Feb 2025
From Chunks to Blocks: Accelerating Uploads and Downloads on the Huboriginal β†—
12 Feb 2025
Build awesome datasets for video generationoriginal β†—
12 Feb 2025
Open R1: Update #2original β†—
10 Feb 2025
The Open Arabic LLM Leaderboard 2original β†—
10 Feb 2025
Open-source DeepResearch – Freeing our search agentsoriginal β†—
4 Feb 2025
Ο€0 and Ο€0-FAST: Vision-Language-Action Models for General Robot Controloriginal β†—
4 Feb 2025
DABStep: Data Agent Benchmark for Multi-step Reasoningoriginal β†—
4 Feb 2025
Open-R1: Update #1original β†—
2 Feb 2025
Mini-R1: Reproduce Deepseek R1 β€žaha momentβ€œ a RL tutorialoriginal β†—
31 Jan 2025
The AI tools for Art Newsletter - Issue 1original β†—
31 Jan 2025
How to deploy and fine-tune DeepSeek models on AWSoriginal β†—
30 Jan 2025
Welcome to Inference Providers on the Hub πŸ”₯original β†—
28 Jan 2025
Open-R1: a fully open reproduction of DeepSeek-R1original β†—
28 Jan 2025
State of open video generation models in Diffusersoriginal β†—
27 Jan 2025
We now support VLMs in smolagents!original β†—
24 Jan 2025
Mastering Long Contexts in LLMs with KVPressoriginal β†—
23 Jan 2025
SmolVLM Grows Smaller – Introducing the 256M & 500M Models!original β†—
23 Jan 2025
Hugging Face and FriendliAI partner to supercharge model deployment on the Huboriginal β†—
22 Jan 2025
Yay! Organizations can now publish blog Articlesoriginal β†—
20 Jan 2025
Timm ❀️ Transformers: Use any timm model with transformersoriginal β†—
16 Jan 2025
Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inferenceoriginal β†—
16 Jan 2025
Train 400x faster Static Embedding Models with Sentence Transformersoriginal β†—
15 Jan 2025
AI Agents Are Here. What Now?original β†—
13 Jan 2025
Visual Document Retrieval Goes Multilingualoriginal β†—
10 Jan 2025
COβ‚‚ Emissions and Models Performance: Insights from the Open LLM Leaderboardoriginal β†—
9 Jan 2025

2024

Introducing smolagents: simple agents that write actions in code.original β†—
31 Dec 2024
Visualize and understand GPU memory in PyTorchoriginal β†—
24 Dec 2024
Controlling Language Model Generation with NVIDIA's LogitsProcessorZoooriginal β†—
23 Dec 2024
Evaluating Audio Reasoning with Big Bench Audiooriginal β†—
20 Dec 2024
Finally, a Replacement for BERT: Introducing ModernBERToriginal β†—
19 Dec 2024
Bamba: Inference-Efficient Hybrid Mamba2 Modeloriginal β†—
18 Dec 2024
Welcome to the Falcon 3 Family of Open Models!original β†—
17 Dec 2024
Benchmarking Language Model Performance on 5th Gen Xeon at GCPoriginal β†—
17 Dec 2024
Introducing the Synthetic Data Generator - Build Datasets with Natural Languageoriginal β†—
16 Dec 2024
LeMaterial: an open source initiative to accelerate materials discovery and researchoriginal β†—
10 Dec 2024
Hugging Face models in Amazon Bedrockoriginal β†—
9 Dec 2024
Open Preference Dataset for Text-to-Image Generation by the πŸ€— Communityoriginal β†—
9 Dec 2024
Welcome PaliGemma 2 – New vision language models by Googleoriginal β†—
5 Dec 2024
How good are LLMs at fixing their mistakes? A chatbot arena experiment with Keras and TPUsoriginal β†—
5 Dec 2024
Rethinking LLM Evaluation with 3C3H: AraGen Benchmark and Leaderboardoriginal β†—
4 Dec 2024
Investing in Performance: Fine-tune small models with LLM insights - a CFM case studyoriginal β†—
3 Dec 2024
Open Source Developers Guide to the EU AI Actoriginal β†—
2 Dec 2024
Rearchitecting Hugging Face Uploads and Downloadsoriginal β†—
26 Nov 2024
SmolVLM - small yet mighty Vision Language Modeloriginal β†—
26 Nov 2024
You could have designed state of the art positional encodingoriginal β†—
25 Nov 2024
Letting Large Models Debate: The First Multilingual LLM Debate Competitionoriginal β†—
20 Nov 2024
From Files to Chunks: Improving HF Storage Efficiencyoriginal β†—
20 Nov 2024
Faster Text Generation with Self-Speculative Decodingoriginal β†—
20 Nov 2024
Introducing the Open Leaderboard for Japanese LLMs!original β†—
20 Nov 2024
Judge Arena: Benchmarking LLMs as Evaluatorsoriginal β†—
19 Nov 2024
Share your open ML datasets on Hugging Face Hub!original β†—
12 Nov 2024
Hugging Face + PyCharmoriginal β†—
5 Nov 2024
Argilla 2.4: Easily Build Fine-Tuning and Evaluation Datasets on the Hub β€” No Code Requiredoriginal β†—
4 Nov 2024
Universal Assisted Generation: Faster Decoding with Any Assistant Modeloriginal β†—
29 Oct 2024
Expert Support case study: Bolstering a RAG app with LLM-as-a-Judgeoriginal β†—
28 Oct 2024
A Deepdive into Aya Expanse: Advancing the Frontier of Multilingualityoriginal β†—
24 Oct 2024
Introducing SynthID Textoriginal β†—
23 Oct 2024
Introducing HUGS - Scale your AI with Open Modelsoriginal β†—
23 Oct 2024
CinePile 2.0 - making stronger datasets with adversarial refinementoriginal β†—
23 Oct 2024
Hugging Face Teams Up with Protect AI: Enhancing Model Security for the ML Communityoriginal β†—
22 Oct 2024
Previous Next