41554 blogs · [ { "id": "01a07d5d-72e9-73ac-bc80-428072557351", "title": "Introducing Idefics2: A Powerful 8B Vision-Language Model for the community", "url": "https://huggingface.co/blog/idefics2", "published_at": "2024-04-15T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280728edd47", "title": "Vision Language Models Explained", "url": "https://huggingface.co/blog/vlms", "published_at": "2024-04-11T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428072e83342", "title": "Making thousands of open LLMs bloom in the Vertex AI Model Garden", "url": "https://huggingface.co/blog/google-cloud-model-garden", "published_at": "2024-04-10T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42807397561f", "title": "CodeGemma - an official Google release for code LLMs", "url": "https://huggingface.co/blog/codegemma", "published_at": "2024-04-09T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428073a47339", "title": "Public Policy at Hugging Face", "url": "https://huggingface.co/blog/policy-blog", "published_at": "2024-04-08T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428074519de0", "title": "Hugging Face partners with Wiz Research to Improve AI Security", "url": "https://huggingface.co/blog/hugging-face-wiz-security-blog", "published_at": "2024-04-04T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42807498364e", "title": "Text2SQL using Hugging Face Dataset Viewer API and Motherduck DuckDB-NSQL-7B", "url": "https://huggingface.co/blog/duckdb-nsql-7b", "published_at": "2024-04-04T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42807553ec1e", "title": "Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon", "url": "https://huggingface.co/blog/setfit-optimum-intel", "published_at": "2024-04-03T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42807624fe78", "title": "Bringing serverless GPU inference to Hugging Face users", "url": "https://huggingface.co/blog/cloudflare-workers-ai", "published_at": "2024-04-02T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428076fd172f", "title": "Pollen-Vision: Unified interface for Zero-Shot vision models in robotics", "url": "https://huggingface.co/blog/pollen-vision", "published_at": "2024-03-25T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42807748b375", "title": "Total noob’s intro to Hugging Face Transformers", "url": "https://huggingface.co/blog/noob_intro_transformers", "published_at": "2024-03-22T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428077e2200d", "title": "Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval", "url": "https://huggingface.co/blog/embedding-quantization", "published_at": "2024-03-22T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280789a53d2", "title": "Introducing the Chatbot Guardrails Arena", "url": "https://huggingface.co/blog/arena-lighthouz", "published_at": "2024-03-21T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428078dee18b", "title": "A Chatbot on your Laptop: Phi-2 on Intel Meteor Lake", "url": "https://huggingface.co/blog/phi2-intel-meteor-lake", "published_at": "2024-03-20T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428079634351", "title": "Cosmopedia: how to create large-scale synthetic data for pre-training Large Language Models", "url": "https://huggingface.co/blog/cosmopedia", "published_at": "2024-03-20T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42807a3fda8f", "title": "GaLore: Advancing Large Model Training on Consumer-grade Hardware", "url": "https://huggingface.co/blog/galore", "published_at": "2024-03-20T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42807a855100", "title": "Easily Train Models with H100 GPUs on NVIDIA DGX Cloud", "url": "https://huggingface.co/blog/train-dgx-cloud", "published_at": "2024-03-18T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42807b7b8ee5", "title": "Quanto: a PyTorch quantization backend for Optimum", "url": "https://huggingface.co/blog/quanto-introduction", "published_at": "2024-03-18T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42807c2e69e5", "title": "CPU Optimized Embeddings with 🤗 Optimum Intel and fastRAG", "url": "https://huggingface.co/blog/intel-fast-embedding", "published_at": "2024-03-15T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42807c6d51a2", "title": "Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset", "url": "https://huggingface.co/blog/websight", "published_at": "2024-03-15T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42807d4dc10f", "title": "Introducing ConTextual: How well can your Multimodal model jointly reason over text and image in text-rich scenes?", "url": "https://huggingface.co/blog/leaderboard-contextual", "published_at": "2024-03-05T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42807de2c27c", "title": "Data is better together: Enabling communities to collectively build better datasets together using Argilla and Hugging Face Spaces", "url": "https://huggingface.co/blog/community-datasets", "published_at": "2024-03-04T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42807e0f581d", "title": "Text-Generation Pipeline on Intel® Gaudi® 2 AI Accelerator", "url": "https://huggingface.co/blog/textgen-pipe-gaudi", "published_at": "2024-02-29T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42807e2b5a12", "title": "StarCoder2 and The Stack v2", "url": "https://huggingface.co/blog/starcoder2", "published_at": "2024-02-28T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42807ea7d43c", "title": "TTS Arena: Benchmarking Text-to-Speech Models in the Wild", "url": "https://huggingface.co/blog/arena-tts", "published_at": "2024-02-27T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42807fa44a30", "title": "AI Watermarking 101: Tools and Techniques", "url": "https://huggingface.co/blog/watermarking", "published_at": "2024-02-26T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280805fd6e1", "title": "Fine-Tuning Gemma Models in Hugging Face", "url": "https://huggingface.co/blog/gemma-peft", "published_at": "2024-02-23T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42808118f555", "title": "Introducing the Red-Teaming Resistance Leaderboard", "url": "https://huggingface.co/blog/leaderboard-haizelab", "published_at": "2024-02-23T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428081b182ad", "title": "🪆 Introduction to Matryoshka Embedding Models", "url": "https://huggingface.co/blog/matryoshka", "published_at": "2024-02-23T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428082789fd2", "title": "Welcome Gemma - Google’s new open LLM", "url": "https://huggingface.co/blog/gemma", "published_at": "2024-02-21T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428082f756a4", "title": "Introducing the Open Ko-LLM Leaderboard: Leading the Korean LLM Evaluation Ecosystem", "url": "https://huggingface.co/blog/leaderboard-upstage", "published_at": "2024-02-20T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428083e4e26e", "title": "🤗 PEFT welcomes new merging methods", "url": "https://huggingface.co/blog/peft_merging", "published_at": "2024-02-19T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280849cf790", "title": "Synthetic data: save money, time and carbon with open source", "url": "https://huggingface.co/blog/synthetic-data-save-costs", "published_at": "2024-02-16T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42808513b6d7", "title": "AMD Pervasive AI Developer Contest!", "url": "https://huggingface.co/blog/amd_pervasive_developer_ai_contest", "published_at": "2024-02-14T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280857e6048", "title": "From OpenAI to Open LLMs with Messages API on Hugging Face", "url": "https://huggingface.co/blog/tgi-messages-api", "published_at": "2024-02-08T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428086091df6", "title": "SegMoE: Segmind Mixture of Diffusion Experts", "url": "https://huggingface.co/blog/segmoe", "published_at": "2024-02-03T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42808643d977", "title": "NPHardEval Leaderboard: Unveiling the Reasoning Abilities of Large Language Models through Complexity Classes and Dynamic Updates", "url": "https://huggingface.co/blog/leaderboard-nphardeval", "published_at": "2024-02-02T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428086b247fc", "title": "Constitutional AI with Open LLMs", "url": "https://huggingface.co/blog/constitutional_ai", "published_at": "2024-02-01T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428086ebfe7c", "title": "Hugging Face Text Generation Inference available for AWS Inferentia2", "url": "https://huggingface.co/blog/text-generation-inference-on-inferentia2", "published_at": "2024-02-01T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428087d7d8ae", "title": "Patch Time Series Transformer in Hugging Face", "url": "https://huggingface.co/blog/patchtst", "published_at": "2024-02-01T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428087db8856", "title": "Introducing the Enterprise Scenarios Leaderboard: a Leaderboard for Real World Use Cases", "url": "https://huggingface.co/blog/leaderboard-patronus", "published_at": "2024-01-31T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428088993a2a", "title": "Accelerate StarCoder with 🤗 Optimum Intel on Xeon: Q8/Q4 and Speculative Decoding", "url": "https://huggingface.co/blog/intel-starcoder-quantization", "published_at": "2024-01-30T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280892454f3", "title": "The Hallucinations Leaderboard, an Open Effort to Measure Hallucinations in Large Language Models", "url": "https://huggingface.co/blog/leaderboard-hallucinations", "published_at": "2024-01-29T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428089d983e3", "title": "An Introduction to AI Secure LLM Safety Leaderboard", "url": "https://huggingface.co/blog/leaderboard-decodingtrust", "published_at": "2024-01-26T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42808ad4818a", "title": "Hugging Face and Google partner for open AI collaboration", "url": "https://huggingface.co/blog/gcp-partnership", "published_at": "2024-01-25T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42808b731715", "title": "Open-source LLMs as LangChain Agents", "url": "https://huggingface.co/blog/open-source-llms-as-agents", "published_at": "2024-01-24T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42808b78f006", "title": "Fine-Tune W2V2-Bert for low-resource ASR with 🤗 Transformers", "url": "https://huggingface.co/blog/fine-tune-w2v2-bert", "published_at": "2024-01-19T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42808c51faa5", "title": "PatchTSMixer in HuggingFace", "url": "https://huggingface.co/blog/patchtsmixer", "published_at": "2024-01-19T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42808cfe62a5", "title": "Preference Tuning LLMs with Direct Preference Optimization Methods", "url": "https://huggingface.co/blog/pref-tuning", "published_at": "2024-01-18T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42808d2f33a8", "title": "Accelerating SD Turbo and SDXL Turbo Inference with ONNX Runtime and Olive", "url": "https://huggingface.co/blog/sdxl_ort_inference", "published_at": "2024-01-15T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42808dfbc427", "title": "Run ComfyUI workflows for free with Gradio on Hugging Face Spaces", "url": "https://huggingface.co/blog/run-comfyui-workflows-on-spaces", "published_at": "2024-01-14T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42808e7a7a9a", "title": "A guide to setting up your own Hugging Face leaderboard: an end-to-end example with Vectara's hallucination leaderboard", "url": "https://huggingface.co/blog/leaderboard-vectara", "published_at": "2024-01-12T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42808ebd9989", "title": "Make LLM Fine-tuning 2x faster with Unsloth and 🤗 TRL", "url": "https://huggingface.co/blog/unsloth-trl", "published_at": "2024-01-10T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42808f24c69e", "title": "Welcome aMUSEd: Efficient Text-to-Image Generation", "url": "https://huggingface.co/blog/amused", "published_at": "2024-01-04T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42808f388732", "title": "LoRA training scripts of the world, unite!", "url": "https://huggingface.co/blog/sdxl_lora_advanced_script", "published_at": "2024-01-02T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42808f7c3fa8", "title": "Speculative Decoding for 2x Faster Whisper Inference", "url": "https://huggingface.co/blog/whisper-speculative-decoding", "published_at": "2023-12-20T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42809015131b", "title": "2023, year of open LLMs", "url": "https://huggingface.co/blog/2023-in-llms", "published_at": "2023-12-18T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42809059b299", "title": "Welcome Mixtral - a SOTA Mixture of Experts on Hugging Face", "url": "https://huggingface.co/blog/mixtral", "published_at": "2023-12-11T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280912d99d6", "title": "Mixture of Experts Explained", "url": "https://huggingface.co/blog/moe", "published_at": "2023-12-11T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428091496ca8", "title": "SetFitABSA: Few-Shot Aspect Based Sentiment Analysis using SetFit", "url": "https://huggingface.co/blog/setfit-absa", "published_at": "2023-12-06T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42809193a087", "title": "AMD + 🤗: Large Language Models Out-of-the-Box Acceleration with AMD GPU", "url": "https://huggingface.co/blog/huggingface-and-optimum-amd", "published_at": "2023-12-05T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428091b53c7d", "title": "Optimum-NVIDIA Unlocking blazingly fast LLM inference in just 1 line of code", "url": "https://huggingface.co/blog/optimum-nvidia", "published_at": "2023-12-05T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428091f75f9b", "title": "Goodbye cold boot - how we made LoRA Inference 300% faster", "url": "https://huggingface.co/blog/lora-adapters-dynamic-loading", "published_at": "2023-12-05T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428092048180", "title": "Open LLM Leaderboard: DROP deep dive", "url": "https://huggingface.co/blog/open-llm-leaderboard-drop", "published_at": "2023-12-01T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428092dbffa2", "title": "SDXL in 4 steps with Latent Consistency LoRAs", "url": "https://huggingface.co/blog/lcm_lora", "published_at": "2023-11-09T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428092edee60", "title": "Make your llama generation time fly with AWS Inferentia2", "url": "https://huggingface.co/blog/inferentia-llama2", "published_at": "2023-11-07T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280933a2756", "title": "Introducing Prodigy-HF: a direct integration with Hugging Face", "url": "https://huggingface.co/blog/prodigy-hf", "published_at": "2023-11-07T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280938132e2", "title": "Comparing the Performance of LLMs: A Deep Dive into Roberta, Llama 2, and Mistral for Disaster Tweets Analysis with Lora", "url": "https://huggingface.co/blog/Lora-for-sequence-classification-with-Roberta-Llama-Mistral", "published_at": "2023-11-07T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428093ea317b", "title": "Introducing Storage Regions on the HF Hub", "url": "https://huggingface.co/blog/regions", "published_at": "2023-11-03T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280944b9549", "title": "Personal Copilot: Train Your Own Coding Assistant", "url": "https://huggingface.co/blog/personal-copilot", "published_at": "2023-10-27T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428094d64193", "title": "Interactively explore your Huggingface dataset with one line of code", "url": "https://huggingface.co/blog/scalable-data-inspection", "published_at": "2023-10-25T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428095a771f3", "title": "Deploy Embedding Models with Hugging Face Inference Endpoints", "url": "https://huggingface.co/blog/inference-endpoints-embeddings", "published_at": "2023-10-24T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428095e8a0b8", "title": "The N Implementation Details of RLHF with PPO", "url": "https://huggingface.co/blog/the_n_implementation_details_of_rlhf_with_ppo", "published_at": "2023-10-24T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428096376756", "title": "Exploring simple optimizations for SDXL", "url": "https://huggingface.co/blog/simple_sdxl_optimizations", "published_at": "2023-10-24T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428096e7aa0e", "title": "Gradio-Lite: Serverless Gradio Running Entirely in Your Browser", "url": "https://huggingface.co/blog/gradio-lite", "published_at": "2023-10-19T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280975ee485", "title": "Accelerating over 130,000 Hugging Face models with ONNX Runtime", "url": "https://huggingface.co/blog/ort-accelerating-hf-models", "published_at": "2023-10-04T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428098185332", "title": "🧨 Accelerating Stable Diffusion XL Inference with JAX on Cloud TPU v5e", "url": "https://huggingface.co/blog/sdxl_jax", "published_at": "2023-10-03T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428098d4d7c9", "title": "Chat Templates: An End to the Silent Performance Killer", "url": "https://huggingface.co/blog/chat-templates", "published_at": "2023-10-03T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-428099af6218", "title": "Deploying the AI Comic Factory using the Inference API", "url": "https://huggingface.co/blog/ai-comic-factory", "published_at": "2023-10-02T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42809a6dab8b", "title": "Ethics and Society Newsletter #5: Hugging Face Goes To Washington and Other Summer 2023 Musings", "url": "https://huggingface.co/blog/ethics-soc-5", "published_at": "2023-09-29T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42809b3686fb", "title": "Finetune Stable Diffusion Models with DDPO via TRL", "url": "https://huggingface.co/blog/trl-ddpo", "published_at": "2023-09-29T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42809bb8f3b2", "title": "Non-engineers guide: Train a LLaMA 2 chatbot", "url": "https://huggingface.co/blog/Llama2-for-non-engineers", "published_at": "2023-09-28T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42809c820ca8", "title": "Llama 2 on Amazon SageMaker a Benchmark", "url": "https://huggingface.co/blog/llama-sagemaker-benchmark", "published_at": "2023-09-26T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42809cbcd3b0", "title": "Inference for PROs", "url": "https://huggingface.co/blog/inference-pro", "published_at": "2023-09-22T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42809d296beb", "title": "Rocket Money x Hugging Face: Scaling Volatile ML Models in Production", "url": "https://huggingface.co/blog/rocketmoney-case-study", "published_at": "2023-09-19T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42809e04c387", "title": "Introduction to 3D Gaussian Splatting", "url": "https://huggingface.co/blog/gaussian-splatting", "published_at": "2023-09-18T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42809e63d45a", "title": "Object Detection Leaderboard", "url": "https://huggingface.co/blog/object-detection-leaderboard", "published_at": "2023-09-18T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42809f456fdc", "title": "Optimizing your LLM in production", "url": "https://huggingface.co/blog/optimize-llm", "published_at": "2023-09-15T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-42809fb18eda", "title": "Introducing Würstchen: Fast Diffusion for Image Generation", "url": "https://huggingface.co/blog/wuerstchen", "published_at": "2023-09-13T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280a0770e2d", "title": "Fine-tuning Llama 2 70B using PyTorch FSDP", "url": "https://huggingface.co/blog/ram-efficient-pytorch-fsdp", "published_at": "2023-09-13T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280a08695a8", "title": "Overview of natively supported quantization schemes in 🤗 Transformers", "url": "https://huggingface.co/blog/overview-quantization-transformers", "published_at": "2023-09-12T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280a0bcd6d9", "title": "SafeCoder vs. Closed-source Code Assistants", "url": "https://huggingface.co/blog/safecoder-vs-closed-source-code-assistants", "published_at": "2023-09-11T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280a16d6532", "title": "Efficient Controllable Generation for SDXL with T2I-Adapters", "url": "https://huggingface.co/blog/t2i-sdxl-adapters", "published_at": "2023-09-08T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280a193e80c", "title": "Spread Your Wings: Falcon 180B is here", "url": "https://huggingface.co/blog/falcon-180b", "published_at": "2023-09-06T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280a25ff2de", "title": "Fetch Cuts ML Processing Latency by 50% Using Amazon SageMaker & Hugging Face", "url": "https://huggingface.co/blog/fetch-case-study", "published_at": "2023-09-01T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280a280f665", "title": "AudioLDM 2, but faster ⚡️", "url": "https://huggingface.co/blog/audioldm2", "published_at": "2023-08-30T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280a31c512d", "title": "Code Llama: Llama 2 learns to code", "url": "https://huggingface.co/blog/codellama", "published_at": "2023-08-25T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280a385e195", "title": "Deprecation of Git Authentication using password", "url": "https://huggingface.co/blog/password-git-deprecation", "published_at": "2023-08-25T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280a47bde60", "title": "Making LLMs lighter with AutoGPTQ and transformers", "url": "https://huggingface.co/blog/gptq-integration", "published_at": "2023-08-23T00:00:00+00:00" }, { "id": "01a07d5d-72e9-73ac-bc80-4280a47c6026", "title": "Introducing SafeCoder", "url": "https://huggingface.co/blog/safecoder", "published_at": "2023-08-22T00:00:00+00:00" } ] posts Claim your blog

Back to Hugging Face

Blog · corpus.blog/blogs/huggingface.co/posts

Hugging Face

huggingface.co

2024

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community original ↗

15 Apr 2024

Vision Language Models Explained original ↗

11 Apr 2024

Making thousands of open LLMs bloom in the Vertex AI Model Garden original ↗

10 Apr 2024

CodeGemma - an official Google release for code LLMs original ↗

9 Apr 2024

Public Policy at Hugging Face original ↗

8 Apr 2024

Hugging Face partners with Wiz Research to Improve AI Security original ↗

4 Apr 2024

Text2SQL using Hugging Face Dataset Viewer API and Motherduck DuckDB-NSQL-7B original ↗

4 Apr 2024

Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon original ↗

3 Apr 2024

Bringing serverless GPU inference to Hugging Face users original ↗

2 Apr 2024

Pollen-Vision: Unified interface for Zero-Shot vision models in robotics original ↗

25 Mar 2024

Total noob’s intro to Hugging Face Transformers original ↗

22 Mar 2024

Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval original ↗

22 Mar 2024

Introducing the Chatbot Guardrails Arena original ↗

21 Mar 2024

A Chatbot on your Laptop: Phi-2 on Intel Meteor Lake original ↗

20 Mar 2024

Cosmopedia: how to create large-scale synthetic data for pre-training Large Language Models original ↗

20 Mar 2024

GaLore: Advancing Large Model Training on Consumer-grade Hardware original ↗

20 Mar 2024

Easily Train Models with H100 GPUs on NVIDIA DGX Cloud original ↗

18 Mar 2024

Quanto: a PyTorch quantization backend for Optimum original ↗

18 Mar 2024

CPU Optimized Embeddings with 🤗 Optimum Intel and fastRAG original ↗

15 Mar 2024

Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset original ↗

15 Mar 2024

Introducing ConTextual: How well can your Multimodal model jointly reason over text and image in text-rich scenes?original ↗

5 Mar 2024

Data is better together: Enabling communities to collectively build better datasets together using Argilla and Hugging Face Spaces original ↗

4 Mar 2024

Text-Generation Pipeline on Intel® Gaudi® 2 AI Accelerator original ↗

29 Feb 2024

StarCoder2 and The Stack v2 original ↗

28 Feb 2024

TTS Arena: Benchmarking Text-to-Speech Models in the Wild original ↗

27 Feb 2024

AI Watermarking 101: Tools and Techniques original ↗

26 Feb 2024

Fine-Tuning Gemma Models in Hugging Face original ↗

23 Feb 2024

Introducing the Red-Teaming Resistance Leaderboard original ↗

23 Feb 2024

🪆 Introduction to Matryoshka Embedding Models original ↗

23 Feb 2024

Welcome Gemma - Google’s new open LLM original ↗

21 Feb 2024

Introducing the Open Ko-LLM Leaderboard: Leading the Korean LLM Evaluation Ecosystem original ↗

20 Feb 2024

🤗 PEFT welcomes new merging methods original ↗

19 Feb 2024

Synthetic data: save money, time and carbon with open source original ↗

16 Feb 2024

AMD Pervasive AI Developer Contest!original ↗

14 Feb 2024

From OpenAI to Open LLMs with Messages API on Hugging Face original ↗

8 Feb 2024

SegMoE: Segmind Mixture of Diffusion Experts original ↗

3 Feb 2024

NPHardEval Leaderboard: Unveiling the Reasoning Abilities of Large Language Models through Complexity Classes and Dynamic Updates original ↗

2 Feb 2024

Constitutional AI with Open LLMs original ↗

1 Feb 2024

Hugging Face Text Generation Inference available for AWS Inferentia2 original ↗

1 Feb 2024

Patch Time Series Transformer in Hugging Face original ↗

1 Feb 2024

Introducing the Enterprise Scenarios Leaderboard: a Leaderboard for Real World Use Cases original ↗

31 Jan 2024

Accelerate StarCoder with 🤗 Optimum Intel on Xeon: Q8/Q4 and Speculative Decoding original ↗

30 Jan 2024

The Hallucinations Leaderboard, an Open Effort to Measure Hallucinations in Large Language Models original ↗

29 Jan 2024

An Introduction to AI Secure LLM Safety Leaderboard original ↗

26 Jan 2024

Hugging Face and Google partner for open AI collaboration original ↗

25 Jan 2024

Open-source LLMs as LangChain Agents original ↗

24 Jan 2024

Fine-Tune W2V2-Bert for low-resource ASR with 🤗 Transformers original ↗

19 Jan 2024

PatchTSMixer in HuggingFace original ↗

19 Jan 2024

Preference Tuning LLMs with Direct Preference Optimization Methods original ↗

18 Jan 2024

Accelerating SD Turbo and SDXL Turbo Inference with ONNX Runtime and Olive original ↗

15 Jan 2024

Run ComfyUI workflows for free with Gradio on Hugging Face Spaces original ↗

14 Jan 2024

A guide to setting up your own Hugging Face leaderboard: an end-to-end example with Vectara's hallucination leaderboard original ↗

12 Jan 2024

Make LLM Fine-tuning 2x faster with Unsloth and 🤗 TRL original ↗

10 Jan 2024

Welcome aMUSEd: Efficient Text-to-Image Generation original ↗

4 Jan 2024

LoRA training scripts of the world, unite!original ↗

2 Jan 2024

2023

Speculative Decoding for 2x Faster Whisper Inference original ↗

20 Dec 2023

2023, year of open LLMs original ↗

18 Dec 2023

Welcome Mixtral - a SOTA Mixture of Experts on Hugging Face original ↗

11 Dec 2023

Mixture of Experts Explained original ↗

11 Dec 2023

SetFitABSA: Few-Shot Aspect Based Sentiment Analysis using SetFit original ↗

6 Dec 2023

AMD + 🤗: Large Language Models Out-of-the-Box Acceleration with AMD GPU original ↗

5 Dec 2023

Optimum-NVIDIA Unlocking blazingly fast LLM inference in just 1 line of code original ↗

5 Dec 2023

Goodbye cold boot - how we made LoRA Inference 300% faster original ↗

5 Dec 2023

Open LLM Leaderboard: DROP deep dive original ↗

1 Dec 2023

SDXL in 4 steps with Latent Consistency LoRAs original ↗

9 Nov 2023

Make your llama generation time fly with AWS Inferentia2 original ↗

7 Nov 2023

Introducing Prodigy-HF: a direct integration with Hugging Face original ↗

7 Nov 2023

Comparing the Performance of LLMs: A Deep Dive into Roberta, Llama 2, and Mistral for Disaster Tweets Analysis with Lora original ↗

7 Nov 2023

Introducing Storage Regions on the HF Hub original ↗

3 Nov 2023

Personal Copilot: Train Your Own Coding Assistant original ↗

27 Oct 2023

Interactively explore your Huggingface dataset with one line of code original ↗

25 Oct 2023

Deploy Embedding Models with Hugging Face Inference Endpoints original ↗

24 Oct 2023

The N Implementation Details of RLHF with PPO original ↗

24 Oct 2023

Exploring simple optimizations for SDXL original ↗

24 Oct 2023

Gradio-Lite: Serverless Gradio Running Entirely in Your Browser original ↗

19 Oct 2023

Accelerating over 130,000 Hugging Face models with ONNX Runtime original ↗

4 Oct 2023

🧨 Accelerating Stable Diffusion XL Inference with JAX on Cloud TPU v5e original ↗

3 Oct 2023

Chat Templates: An End to the Silent Performance Killer original ↗

3 Oct 2023

Deploying the AI Comic Factory using the Inference API original ↗

2 Oct 2023

Ethics and Society Newsletter #5: Hugging Face Goes To Washington and Other Summer 2023 Musings original ↗

29 Sept 2023

Finetune Stable Diffusion Models with DDPO via TRL original ↗

29 Sept 2023

Non-engineers guide: Train a LLaMA 2 chatbot original ↗

28 Sept 2023

Llama 2 on Amazon SageMaker a Benchmark original ↗

26 Sept 2023

Inference for PROs original ↗

22 Sept 2023

Rocket Money x Hugging Face: Scaling Volatile ML Models in Productionoriginal ↗

19 Sept 2023

Introduction to 3D Gaussian Splatting original ↗

18 Sept 2023

Object Detection Leaderboard original ↗

18 Sept 2023

Optimizing your LLM in production original ↗

15 Sept 2023

Introducing Würstchen: Fast Diffusion for Image Generation original ↗

13 Sept 2023

Fine-tuning Llama 2 70B using PyTorch FSDP original ↗

13 Sept 2023

Overview of natively supported quantization schemes in 🤗 Transformers original ↗

12 Sept 2023

SafeCoder vs. Closed-source Code Assistants original ↗

11 Sept 2023

Efficient Controllable Generation for SDXL with T2I-Adapters original ↗

8 Sept 2023

Spread Your Wings: Falcon 180B is here original ↗

6 Sept 2023

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

1 Sept 2023

AudioLDM 2, but faster ⚡️original ↗

30 Aug 2023

Code Llama: Llama 2 learns to code original ↗

25 Aug 2023

Deprecation of Git Authentication using password original ↗

25 Aug 2023

Making LLMs lighter with AutoGPTQ and transformers original ↗

23 Aug 2023

Introducing SafeCoder original ↗

22 Aug 2023