The Curious Engineer

All blogs / AI / ML

Hugging Face

huggingface.co/blog

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

AI / ML

’20’21’22’23’24’25’26
Posts
925 from 14 Feb 2020 to 30 Oct 2026
Posting
about daily (230 in the last year)
Kind
company blog
Feed
https://huggingface.co/blog/feed.xml

2026 209

  1. nemotron-halloween
  2. Granite Switch 4.1.1 — Update models like you update software
  3. Announcing Project ProtoStar: Making Publicly Funded Science AI-Ready
  4. Welcome Le Chonk: Mistral Large 4 on Hugging Face
  5. Introducing AnySpeechRecognizer and AnyDecisionModel: Open Models for Speech and Decisions on Apple Platforms
  6. NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt
  7. Build specialized multimodal models with LFM3
  8. Can we trust LLMs to judge whether a research idea is novel?
  9. LitPivot: Developing research ideas through dynamic contextualization within the literature landscape
  10. view all
  11. Does Your Model Run on AWS Trainium? Look It Up
  12. Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox
  13. In financial services, the AI question is moving from the model to where it runs Farsight-AI • about 15 hours ago • 7
  14. OlmoEarth v1.3: State-of-the-art embeddings for the whole planet
  15. Ensemble forecasting with IBM Granite time-series models
  16. Laghu
  17. NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training Required
  18. Train in Simulation, Deploy on a Real Robot: Microduck with Isaac Lab 3.0 nvidia • 1 day ago • 10
  19. How Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real Applications
  20. Profiling TorchNeuron (Part 1): System-level profiling on AWS Trainium.
  21. Granite Speech 5.0: Transcribe, Translate, and Attribute more Accurately and Faster
  22. NVIDIA Kumo Forecast Combines Pretrained Time-Series Representations with Historical Pattern Retrieval and Interpretability nvidia • 2 days ago • 8
  23. NVIDIA Kumo Anomaly Brings Diffusion-Based Anomaly Detection to Multivariate Time Series nvidia • 2 days ago • 6
  24. Announcing SimReady Central: An Open Library of Simulation-Ready 3D Assets for Robotics and AI Factories nvidia • 2 days ago • 18
  25. NVIDIA Nemotron 3.5 Embed, Rerank, and Parse: Advancing Agents with World-Class Retrieval Models nvidia • 2 days ago • 48
  26. Lattice 4D Real-World Dataset LatticeAdmin • 2 days ago • 7
  27. bekko-static-embedding-v1: State-of-the-Art Retrieval for Multilingual Static Embeddings hotchpotch • 2 days ago • 13
  28. NVIDIA Cosmos3-H-Dreams: Bringing Clinical Surgery to Life Through Generative Simulation nvidia • 3 days ago • 14
  29. ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model ibm-research • 3 days ago • 25
  30. A curriculum for post-training agents huggingface • 3 days ago • 10
  31. Do we really need bigger AI weather forecasting models to improve resolution? EmmaScharfmann • 3 days ago • 10
  32. Hugging Face ❤️ TorchTPU: TPUs, Natively
  33. AnyLanguageModel 1.0: One Year of Local Models on Apple Platforms
  34. MPS in PyTorch 2.15
  35. SlideOn & mSlideOn: Sparsified Late-Interaction and Dense Retrievers lightonai • 4 days ago • 23
  36. Sort your prompts: a free speed-up for MoE batch inference badaoui • 4 days ago • 9
  37. TorchNeuron: running HF models on AWS Trainium is easier than ever
  38. Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline nvidia • 7 days ago • 48
  39. Welcome Beam: a 501B open model you can own, customize, and scale
  40. Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint ibm-granite • 7 days ago • 69
  41. View all articles
  42. The Most Intuitive Way to Understand Score Function Centering: Understand Trainer-Generator Mismatch in Async RL from the Score Function NormalUhr • 8 days ago • 11
  43. The Missing Piece in LLM Memory: Why Long Context and Retrieval Aren't Enough for Belief Revision boltwave • 8 days ago • 60
  44. Apertus 1.5 Release Notes
  45. Tokenmaxxing BERT: 50x faster tokenization huggingface • 8 days ago • 51
  46. Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta
  47. Welcome FLUX.3 Image Klein in Diffusers
  48. UltraBERT: One Encoder for Classification and Retrieval dmis-lab • 9 days ago • 61
  49. Run fast, private agents on-device with LFM2.5-24B-A2B
  50. The model that didn't exist, so you made it yourself
  51. Introducing Falcon ASR
  52. The Agent Said It Was Done. The Database Disagreed.
  53. AutoSynthData: Generating Training Data for Enterprise Agents
  54. Open TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning
  55. Getting the Source Right, Not Just the Fact: Source-Aware Verification for MCP Agents
  56. Holo4: powering generalist computer-use agents
  57. Welcome RL Environments to the hub
  58. How UK AISI and EvalEval Are Making Benchmark Results Reproducible
  59. Transformers now runs llama.cpp quants
  60. Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community
  61. tokenizers v1: encode, decode and scaling, measured
  62. Your Agent Aced the Task. Will It Do It Again?
  63. Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL
  64. Rebuilding AUTOMATIC1111 with Gradio Workflow
  65. NeoMME: an efficient Multimodal-native and Multilingual Encoder
  66. Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
  67. Give Your Coding Agents a Memory You Own
  68. Training a coding model to paint watercolours with TRL and OpenEnv
  69. BenchMIRT: What are LLM benchmarks actually measuring?
  70. Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI
  71. The Open ASR Leaderboard Adds Its First Global South Language
  72. Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
  73. Granite 4.2 LLMs: How They're Built
  74. Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original
  75. Wire It, Run It, Deploy It: AI Workflows in Gradio
  76. How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code
  77. Measuring benchmark optimization in speech recognition
  78. Up to 3.2x Faster Inference with LFM2.5-DSpark
  79. How Much Memory Does Your Agent Actually Need?
  80. Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers
  81. Same Cluster, 33 Points More Utilization: What Changed Was the Order
  82. State of Open Models: Summer 2026 Observations
  83. Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets
  84. What We Learned by Reproducing 2,200 papers from ICML
  85. Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis
  86. Thinking of ACE? We Can Do It with Fewer Tokens
  87. Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS
  88. Making Knowledge Distillation Cheap Enough to Run at Scale
  89. Meta is back with Muse Glimmer: local, agentic, multimodal, and open source
  90. Baseten on Hugging Face Inference Providers 🔥
  91. GPU Management: Why Idle GPUs Are the New Grounded Aircraft
  92. NVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical Robotics
  93. Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident
  94. Bringing Nunchaku 4-bit Diffusion Inference to Diffusers
  95. Grabette: an open system to record robot-manipulation data
  96. Newer Models, Same Advantage
  97. Security incident disclosure — July 2026
  98. Model Routing Is Simple. Until It Isn’t.
  99. Welcome Inkling by Thinking Machines
  100. Introducing Real World VoiceEQ: Measuring the human quality of voice AI
  101. Profiling in PyTorch (Part 3): Attention is all you profile
  102. Native-speed vLLM transformers modeling backend
  103. From Hugging Face to Amazon SageMaker Studio in one click
  104. Hugging Face Models on Foundry Managed Compute
  105. Run AI workloads on any cloud, store on Hugging Face: zero-egress storage with SkyPilot
  106. LeRobot v0.6.0: Imagine, Evaluate, Improve
  107. PRX Part 4: Our Data Strategy
  108. 🤗 Kernels: Major Updates
  109. Hugging Face and Cerebras bring Gemma 4 to real-time voice AI
  110. ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration
  111. Why Specialization Is Inevitable
  112. Featuring Every Eval Ever Results on Hugging Face Model Pages
  113. DiScoFormer: One transformer for density and score, across distributions
  114. Run a vLLM Server on HF Jobs in One Command
  115. Accelerating Transformers Fine-Tuning with NVIDIA NeMo AutoModel
  116. Introducing the FFASR Leaderboard: Benchmarking ASR in the Real World
  117. Shipping huggingface_hub every week with AI, open tools, and a human in the loop
  118. Experimenting with the proposed Cross-Origin Storage API in Transformers.js
  119. PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters
  120. We got local models to triage the OpenClaw repo for FREE!*
  121. MosaicLeaks: Can your research agent keep a secret?
  122. Beyond LoRA: Can you beat the most popular fine-tuning technique?
  123. Is it agentic enough? Benchmarking open models on your own tooling
  124. From the Hugging Face Hub to robot hardware with Strands Agents and LeRobot
  125. GLM-5.2: Built for Long-Horizon Tasks
  126. Agentic Resource Discovery: Let agents search
  127. Profiling in PyTorch (Part 2): From nn.Linear to a Fused MLP
  128. How an Agent Built a 3D Paris Gallery by Chaining Two Hugging Face Spaces
  129. Migrating Your GitHub CI to Hugging Face Jobs
  130. The Open Source Community is backing OpenEnv for Agentic RL
  131. Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI
  132. Designing the hf CLI as an agent-optimized way to work with the Hub
  133. Direct Preference Optimization Beyond Chatbots
  134. Adding MCP Tools to Reachy Mini
  135. Holo3.1: Fast & Local Computer Use Agents
  136. Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains
  137. Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic
  138. Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler
  139. Reachy Mini goes fully local
  140. Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL
  141. Harness, Scaffold, and the AI Agent Terms Worth Getting Right
  142. OlmoEarth v1.1: A more efficient family of Earth observation models
  143. Introducing the Ettin Reranker Family
  144. PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend
  145. Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality
  146. Unlocking asynchronicity in continuous batching
  147. Building Blocks for Foundation Model Training and Inference on AWS
  148. vLLM V0 to V1: Correctness Before Corrections in RL
  149. Adding Benchmaxxer Repellant to the Open ASR Leaderboard
  150. Granite 4.1 LLMs: How They’re Built
  151. DeepInfra on Hugging Face Inference Providers 🔥
  152. Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents
  153. How to build scalable web apps with OpenAI's Privacy Filter
  154. DeepSeek-V4: a million-token context that agents can actually use
  155. How to Use Transformers.js in a Chrome Extension
  156. QIMMA قِمّة ⛰: A Quality-First Arabic LLM Leaderboard
  157. AI and the Future of Cybersecurity: Why Openness Matters
  158. Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational Agents
  159. The PR you would have opened yourself
  160. Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers
  161. Inside VAKRA: Reasoning, Tool Use, and Failure Modes of Agents
  162. Meet HoloTab by HCompany. Your AI browser companion.
  163. Waypoint-1.5: Higher-Fidelity Interactive Worlds for Everyday GPUs
  164. Multimodal Embedding & Reranker Models with Sentence Transformers
  165. Safetensors is Joining the PyTorch Foundation
  166. Welcome Gemma 4: Frontier multimodal intelligence on device
  167. Falcon Perception
  168. Any Custom Frontend with Gradio's Backend
  169. Granite 4.0 3B Vision: Compact Multimodal Intelligence for Enterprise Documents
  170. Training mRNA Language Models Across 25 Species for $165
  171. TRL v1.0: Post-Training Library Built to Move with the Field
  172. Liberate your OpenClaw
  173. A New Framework for Evaluating Voice Agents (EVA)
  174. Build a Domain-Specific Embedding Model in Under a Day
  175. State of Open Source on Hugging Face: Spring 2026
  176. Holotron-12B - High Throughput Computer Use Agent
  177. Introducing Storage Buckets on the Hugging Face Hub
  178. Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries
  179. Ulysses Sequence Parallelism: Training with Million-Token Contexts
  180. LeRobot v0.5.0: Scaling Every Dimension
  181. Bringing Robotics AI to Embedded Platforms: Dataset Recording, VLA Fine‑Tuning, and On‑Device Optimizations
  182. Introducing Modular Diffusers - Composable Building Blocks for Diffusion Pipelines
  183. PRX Part 3 — Training a Text-to-Image Model in 24h!
  184. Mixture of Experts (MoEs) in Transformers
  185. GGML and llama.cpp join HF to ensure the long-term progress of Local AI
  186. Train AI models with Unsloth and Hugging Face Jobs for FREE
  187. IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST
  188. One-Shot Any Web App with Gradio's gr.HTML
  189. Custom Kernels for All from Codex and Claude
  190. OpenEnv in Practice: Evaluating Tool-Using Agents in Real-World Environments
  191. Transformers.js v4: Now Available on NPM!
  192. Introducing SyGra Studio
  193. Community Evals: Because we're done trusting black-box leaderboards over the community
  194. H Company's new Holo2 model takes the lead in UI Localization
  195. The Future of the Global Open-Source AI Ecosystem: From DeepSeek to AI+
  196. Training Design for Text-to-Image Models: Lessons from Ablations
  197. Introducing Daggr: Chain apps programmatically, inspect visually
  198. We Got Claude to Build CUDA Kernels and teach open models!
  199. Architectural Choices in China's Open-Source AI Ecosystem: Building Beyond DeepSeek
  200. Alyah ⭐️: Toward Robust Evaluation of Emirati Dialect Capabilities in Arabic LLMs
  201. Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective
  202. AssetOpsBench: Bridging the Gap Between AI Agent Benchmarks and Industrial Reality
  203. One Year Since the “DeepSeek Moment”
  204. Differential Transformer V2
  205. Introducing Waypoint-1: Real-time interactive video diffusion from Overworld
  206. Open Responses: What you need to know
  207. NVIDIA Cosmos Reason 2 Brings Advanced Reasoning To Physical AI
  208. Introducing Falcon-H1-Arabic: Pushing the Boundaries of Arabic Language AI with Hybrid Architecture
  209. NVIDIA brings agents to life with DGX Spark and Reachy Mini

2025 208

  1. AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems
  2. Tokenization in Transformers v5: Simpler, Clearer, and More Modular
  3. The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator
  4. CUGA on Hugging Face: Democratizing Configurable AI Agents
  5. New in llama.cpp: Model Management
  6. Codex is Open Sourcing AI models
  7. Introducing swift-huggingface: The Complete Swift Client for Hugging Face
  8. DeepMath: A lightweight math reasoning Agent with smolagents
  9. We Got Claude to Fine-Tune an Open Source LLM
  10. Transformers v5: Simple model definitions powering the AI ecosystem
  11. Diffusers welcomes FLUX-2
  12. Continuous batching from first principles
  13. Building Deep Research: How we Achieved State of the Art
  14. OVHcloud on Hugging Face Inference Providers 🔥
  15. 20x Faster TRL Fine-tuning with RapidFire AI
  16. Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracks
  17. Introducing AnyLanguageModel: One API for Local and Remote LLMs on Apple Platforms
  18. Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models
  19. Easily Build and Share ROCm Kernels with Hugging Face
  20. Join the AMD Open Robotics Hackathon
  21. Building for an Open Future - our new partnership with Google Cloud
  22. Aligning to What? Rethinking Agent Generalization in MiniMax M2
  23. On the Shifting Global Compute Landscape
  24. Building a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac
  25. How to Build a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac for Healthcare
  26. Granite 4.0 Nano: Just how small can you go?
  27. Voice Cloning with Consent
  28. Streaming datasets: 100x More Efficient
  29. huggingface_hub v1.0: Five Years of Building the Foundation of Open Machine Learning
  30. LeRobot v0.4.0: Supercharging OSS Robot Learning
  31. Building the Open Agent Ecosystem Together: Introducing OpenEnv
  32. Hugging Face and VirusTotal collaborate to strengthen AI security
  33. Sentence Transformers is joining Hugging Face!
  34. Supercharge your OCR Pipelines with Open Models
  35. Unlock the power of images with AI Sheets
  36. AI for Food Allergies
  37. Google Cloud C4 Brings a 70% TCO improvement on GPT OSS with Intel and Hugging Face
  38. Get your VLM running in 3 simple steps on Intel CPUs
  39. Nemotron-Personas-India: Synthesized Data for Sovereign AI
  40. Arm will be @ PyTorch Conference, Join Us!
  41. BigCodeArena: Judging code generations end to end with code executions
  42. SOTA OCR with Core ML and dots.ocr
  43. Introducing RTEB: A New Standard for Retrieval Evaluation
  44. Accelerating Qwen3-8B Agent on Intel® Core™ Ultra with Depth-Pruned Draft Models
  45. VibeGame: Exploring Vibe Coding Games
  46. Nemotron-Personas-Japan: ソブリン AI のための合成データセット
  47. Swift Transformers Reaches 1.0 – and Looks to the Future
  48. Smol2Operator: Post-Training GUI Agents for Computer Use
  49. SyGra: The One-Stop Framework for Building Data for LLMs and SLMs
  50. Gaia2 and ARE: Empowering the community to study agents
  51. Scaleway on Hugging Face Inference Providers 🔥
  52. Democratizing AI Safety with RiskRubric.ai
  53. Public AI on Hugging Face Inference Providers 🔥
  54. `LeRobotDataset:v3.0`: Bringing large-scale datasets to `lerobot`
  55. Visible Watermarking with Gradio
  56. Introducing the Palmyra-mini family: Powerful, lightweight, and ready to reason!
  57. Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers
  58. Fine-tune Any LLM from the Hugging Face Hub with Together AI
  59. Jupyter Agents: training LLMs to reason with notebooks
  60. mmBERT: ModernBERT goes Multilingual
  61. Welcome EmbeddingGemma, Google's new efficient embedding model
  62. SAIR: Accelerating Pharma R&D with AI-Powered Structural Intelligence
  63. Make your ZeroGPU Spaces go brrr with ahead-of-time compilation
  64. NVIDIA Releases 6 Million Multi-Lingual Reasoning Dataset
  65. Generate Images with Claude and Hugging Face
  66. From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels
  67. MCP for Research: How to Connect AI to Research Tools
  68. Kimina-Prover-RL
  69. Kimina-Prover-RL
  70. Arm & ExecuTorch 0.7: Bringing Generative AI to the masses
  71. Neural Super Sampling is here!
  72. TextQuests: How Good are LLMs at Text-Based Video Games?
  73. 🇵🇭 FilBench - Can LLMs Understand and Generate Filipino?
  74. Introducing AI Sheets: a tool to work with datasets using open AI models!
  75. Accelerate ND-Parallel: A guide to Efficient Multi-GPU Training
  76. Vision Language Model Alignment in TRL ⚡️
  77. Welcome GPT OSS, the new open-source model family from OpenAI!
  78. Measuring Open-Source Llama Nemotron Models on DeepResearch Bench
  79. 📚 3LM: A Benchmark for Arabic LLMs in STEM and Code
  80. Implementing MCP Servers in Python: An AI Shopping Assistant with Gradio
  81. Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face
  82. Say hello to `hf`: a faster, friendlier Hugging Face CLI ✨
  83. Parquet Content-Defined Chunking
  84. TimeScope: How Long Can Your Video Large Multimodal Model Go?
  85. Fast LoRA inference for Flux with Diffusers and PEFT
  86. Accelerate a World of LLMs on Hugging Face with NVIDIA NIM
  87. Arc Virtual Cell Challenge: A Primer
  88. Consilium: When Multiple LLMs Collaborate
  89. Back to The Future: Evaluating AI Agents on Predicting Future Events
  90. Five Big Improvements to Gradio MCP Servers
  91. Ettin Suite: SoTA Paired Encoders and Decoders
  92. Migrating the Hub from Git LFS to Xet
  93. Kimina-Prover: Applying Test-time RL Search on Large Formal Reasoning Models
  94. Kimina-Prover: Applying Test-time RL Search on Large Formal Reasoning Models
  95. Asynchronous Robot Inference: Decoupling Action Prediction and Execution
  96. ScreenEnv: Deploy your full stack Desktop Agent
  97. Building the Hugging Face MCP Server
  98. Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders
  99. Creating custom kernels for the AMD MI300
  100. Upskill your LLMs With Gradio MCP Servers
  101. SmolLM3: smol, multilingual, long-context reasoner
  102. Three Mighty Alerts Supporting Hugging Face’s Production Infrastructure
  103. Efficient MultiModal Data Pipeline
  104. Announcing NeurIPS 2025 E2LM Competition: Early Training Evaluation of Language Models
  105. Training and Finetuning Sparse Embedding Models with Sentence Transformers
  106. Welcome the NVIDIA Llama Nemotron Nano VLM to Hugging Face Hub
  107. Gemma 3n fully available in the open-source ecosystem!
  108. Transformers backend integration in SGLang
  109. (LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardware
  110. Groq on Hugging Face Inference Providers 🔥
  111. How Long Prompts Block Other Requests - Optimizing LLM Performance
  112. Learn the Hugging Face Kernel Hub in 5 Minutes
  113. Featherless AI on Hugging Face Inference Providers 🔥
  114. Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Arm
  115. Introducing Training Cluster as a Service - a new collaboration with NVIDIA
  116. ScreenSuite - The most comprehensive evaluation suite for GUI Agents!
  117. KV Cache from scratch in nanoVLM
  118. Real-Time AI Sound Generation on Arm: A Personal Tool for Creative Freedom
  119. Holo1: New family of GUI automation VLMs powering GUI agent Surfer-H
  120. SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data
  121. No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL
  122. CodeAgents + Structure: A Better Way to Execute Actions
  123. 🐯 Liger GRPO meets TRL
  124. Dell Enterprise Hub is all you need to build AI on premises
  125. Tiny Agents in Python: a MCP-powered agent in ~70 lines of code
  126. Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance
  127. Falcon-Arabic: A Breakthrough in Arabic Language Models
  128. Exploring Quantization Backends in Diffusers
  129. nanoVLM: The simplest repository to train your VLM in pure PyTorch
  130. Microsoft and Hugging Face expand collaboration
  131. Falcon-Edge: A series of powerful, universal, fine-tunable 1.58bit language models.
  132. The Transformers Library: standardizing model definitions
  133. Improving Hugging Face Model Access for Kaggle Users
  134. Blazingly fast whisper transcriptions with Inference Endpoints
  135. Vision Language Models (Better, faster, stronger)
  136. LeRobot Community Datasets: The “ImageNet” of Robotics — When and How?
  137. How to Build an MCP Server with Gradio
  138. The 4 Things Qwen-3’s Chat Template Teaches Us
  139. Welcoming Llama Guard 4 on Hugging Face Hub
  140. Introducing AutoRound: Intel’s Advanced Quantization for LLMs and VLMs
  141. PipelineRL
  142. Tiny Agents: an MCP-powered agent in 50 lines of code
  143. Finetuning olmOCR to be a faithful OCR-Engine
  144. Prefill and Decode for Concurrent Requests - Optimizing LLM Performance
  145. 17 Reasons Why Gradio Isn't Just Another UI Library
  146. Cohere on Hugging Face Inference Providers 🔥
  147. Introducing HELMET: Holistically Evaluating Long-context Language Models
  148. Hugging Face to sell open-source robots thanks to Pollen Robotics acquisition 🤖
  149. 4M Models Scanned: Protect AI + Hugging Face 6 Months In
  150. Visual Salamandra: Pushing the Boundaries of Multimodal Understanding
  151. Hugging Face and Cloudflare Partner to Make Real-Time Speech and Video Seamless with FastRTC
  152. Arabic Leaderboards: Introducing Arabic Instruction Following, Updating AraGen, and More
  153. Welcome Llama 4 Maverick & Scout on Hugging Face
  154. Journey to 1 Million Gradio Users!
  155. The NLP Course is becoming the LLM Course
  156. Efficient Request Queueing – Optimizing LLM Performance
  157. How Hugging Face Scaled Secrets Management for AI Infrastructure
  158. 🚀 Accelerating LLM Inference with TGI on Intel Gaudi
  159. Open R1: Update #4
  160. Training and Finetuning Reranker Models with Sentence Transformers
  161. Introducing Gradio's new Dataframe!
  162. The New and Fresh analytics in Inference Endpoints
  163. Open R1: How to use OlympicCoder locally for coding
  164. AI Policy @🤗: Response to the White House AI Action Plan RFI
  165. NVIDIA's GTC 2025 Announcement for Physical AI Developers: New Open Models and Datasets
  166. Xet is on the Hub
  167. Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM
  168. Open R1: Update #3
  169. LeRobot goes to driving school: World’s largest open-source self-driving dataset
  170. LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone!
  171. Hugging Face and JFrog partner to make AI Security more transparent
  172. A Deepdive into Aya Vision: Advancing the Frontier of Multilingual Multimodality
  173. Trace & Evaluate your Agent with Arize Phoenix
  174. HuggingFace, IISc partner to supercharge model building on India's diverse languages
  175. FastRTC: The Real-Time Communication Library for Python
  176. Remote VAEs for decoding with Inference Endpoints 🤗
  177. SigLIP 2: A better multilingual vision language encoder
  178. SmolVLM2: Bringing Video Understanding to Every Device
  179. PaliGemma 2 Mix - New Instruction Vision Language Models by Google
  180. Introducing Three New Serverless Inference Providers: Hyperbolic, Nebius AI Studio, and Novita 🔥
  181. Welcome Fireworks.ai on the Hub 🎆
  182. Fixing Open LLM Leaderboard with Math-Verify
  183. 1 Billion Classifications
  184. From Chunks to Blocks: Accelerating Uploads and Downloads on the Hub
  185. Build awesome datasets for video generation
  186. Open R1: Update #2
  187. The Open Arabic LLM Leaderboard 2
  188. Open-source DeepResearch – Freeing our search agents
  189. π0 and π0-FAST: Vision-Language-Action Models for General Robot Control
  190. DABStep: Data Agent Benchmark for Multi-step Reasoning
  191. Open-R1: Update #1
  192. Mini-R1: Reproduce Deepseek R1 „aha moment“ a RL tutorial
  193. The AI tools for Art Newsletter - Issue 1
  194. How to deploy and fine-tune DeepSeek models on AWS
  195. Welcome to Inference Providers on the Hub 🔥
  196. Open-R1: a fully open reproduction of DeepSeek-R1
  197. State of open video generation models in Diffusers
  198. We now support VLMs in smolagents!
  199. Mastering Long Contexts in LLMs with KVPress
  200. SmolVLM Grows Smaller – Introducing the 256M & 500M Models!
  201. Hugging Face and FriendliAI partner to supercharge model deployment on the Hub
  202. Yay! Organizations can now publish blog Articles
  203. Timm ❤️ Transformers: Use any timm model with transformers
  204. Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference
  205. Train 400x faster Static Embedding Models with Sentence Transformers
  206. AI Agents Are Here. What Now?
  207. Visual Document Retrieval Goes Multilingual
  208. CO₂ Emissions and Models Performance: Insights from the Open LLM Leaderboard

2024 190

  1. Introducing smolagents: simple agents that write actions in code.
  2. Visualize and understand GPU memory in PyTorch
  3. Controlling Language Model Generation with NVIDIA's LogitsProcessorZoo
  4. Evaluating Audio Reasoning with Big Bench Audio
  5. Finally, a Replacement for BERT: Introducing ModernBERT
  6. Bamba: Inference-Efficient Hybrid Mamba2 Model
  7. Welcome to the Falcon 3 Family of Open Models!
  8. Benchmarking Language Model Performance on 5th Gen Xeon at GCP
  9. Introducing the Synthetic Data Generator - Build Datasets with Natural Language
  10. LeMaterial: an open source initiative to accelerate materials discovery and research
  11. Hugging Face models in Amazon Bedrock
  12. Open Preference Dataset for Text-to-Image Generation by the 🤗 Community
  13. Welcome PaliGemma 2 – New vision language models by Google
  14. How good are LLMs at fixing their mistakes? A chatbot arena experiment with Keras and TPUs
  15. Rethinking LLM Evaluation with 3C3H: AraGen Benchmark and Leaderboard
  16. Investing in Performance: Fine-tune small models with LLM insights - a CFM case study
  17. Open Source Developers Guide to the EU AI Act
  18. Rearchitecting Hugging Face Uploads and Downloads
  19. SmolVLM - small yet mighty Vision Language Model
  20. You could have designed state of the art positional encoding
  21. Letting Large Models Debate: The First Multilingual LLM Debate Competition
  22. From Files to Chunks: Improving HF Storage Efficiency
  23. Faster Text Generation with Self-Speculative Decoding
  24. Introducing the Open Leaderboard for Japanese LLMs!
  25. Judge Arena: Benchmarking LLMs as Evaluators
  26. Share your open ML datasets on Hugging Face Hub!
  27. Hugging Face + PyCharm
  28. Argilla 2.4: Easily Build Fine-Tuning and Evaluation Datasets on the Hub — No Code Required
  29. Universal Assisted Generation: Faster Decoding with Any Assistant Model
  30. Expert Support case study: Bolstering a RAG app with LLM-as-a-Judge
  31. A Deepdive into Aya Expanse: Advancing the Frontier of Multilinguality
  32. Introducing SynthID Text
  33. Introducing HUGS - Scale your AI with Open Models
  34. CinePile 2.0 - making stronger datasets with adversarial refinement
  35. Hugging Face Teams Up with Protect AI: Enhancing Model Security for the ML Community
  36. Transformers.js v3: WebGPU Support, New Models & Tasks, and More…
  37. Diffusers welcomes Stable Diffusion 3.5 Large
  38. Releasing Outlines-core 0.1.0: structured generation in Rust and Python
  39. Deploying Speech-to-Speech on Hugging Face
  40. “Llama 3.2 in Keras”
  41. Fixing Gradient Accumulation
  42. Introducing the AMD 5th Gen EPYC™ CPU
  43. A Security Review of Gradio 5
  44. Welcome, Gradio 5
  45. Scaling AI-based Data Processing with Hugging Face + Dask
  46. Faster Assisted Generation with Dynamic Speculation
  47. Improving Parquet Dedupe on Hugging Face Hub
  48. Introducing the Open FinLLM Leaderboard
  49. A Short Summary of Chinese AI Global Expansion
  50. 🇨🇿 BenCzechMark - Can your LLM Understand Czech?
  51. Converting Vertex-Colored Meshes to Textured Meshes
  52. Llama can now see and run on your device - welcome Llama 3.2
  53. FineVideo: behind the scenes
  54. Exploring the Daily Papers Page on Hugging Face
  55. Optimize and deploy with Optimum-Intel and OpenVINO GenAI
  56. Fine-tuning LLMs to 1.58bit: extreme quantization made easy
  57. Introducing the SQL Console on Datasets
  58. Introducing Community Tools on HuggingChat
  59. Accelerate 1.0.0
  60. Hugging Face partners with TruffleHog to Scan for Secrets
  61. Scaling robotics datasets with video encoding
  62. The 5 Most Under-Rated Tools on Hugging Face
  63. Improving Hugging Face Training Efficiency Through Packing with Flash Attention 2
  64. Deploy Meta Llama 3.1 405B on Google Cloud Vertex AI
  65. A failed experiment: Infini-Attention, and why we should keep trying?
  66. Introduction to ggml
  67. Welcome Falcon Mamba: The first strong attention-free 7B model
  68. Tool Use, Unified
  69. XetHub is joining Hugging Face!
  70. 2024 Security Feature Highlights
  71. Introducing TextImage Augmentation for Document Images
  72. Google releases Gemma 2 2B, ShieldGemma and Gemma Scope
  73. Memory-efficient Diffusion Transformers with Quanto and Diffusers
  74. Serverless Inference with Hugging Face and NVIDIA NIM
  75. LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?
  76. Llama 3.1 - 405B, 70B & 8B with multilinguality and long context
  77. WWDC 24: Running Mistral 7B with Core ML
  78. Docmatix - a huge dataset for Document Visual Question Answering
  79. TGI Multi-LoRA: Deploy Once, Serve 30 Models
  80. SmolLM - blazingly fast and remarkably powerful
  81. How we leveraged distilabel to create an Argilla 2.0 Chatbot
  82. How NuminaMath Won the 1st AIMO Progress Prize
  83. Announcing New Hugging Face and KerasHub integration
  84. Experimenting with Automatic PII Detection on the Hub using Presidio
  85. Preference Optimization for Vision Language Models
  86. Google Cloud TPUs made available to Hugging Face users
  87. Banque des Territoires (CDC Group) x Polyconseil x Hugging Face: Enhancing a Major French Environmental Program with a Sovereign Data Solution
  88. Announcing New Dataset Search Features
  89. Accelerating Protein Language Model ProtST on Intel Gaudi 2
  90. Our Transformers Code Agent beats the GAIA benchmark 🏅
  91. Welcome Gemma 2 - Google’s new open LLM
  92. XLSCOUT Unveils ParaEmbed 2.0: a Powerful Embedding Model Tailored for Patents and IP with Expert Support from Hugging Face
  93. Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models
  94. Ethics and Society Newsletter #6: Building Better AI: The Importance of Data Quality
  95. Data Is Better Together: A Look Back and Forward
  96. Going multimodal: How Prezi is leveraging the Hub and the Expert Support Program to accelerate their ML roadmap
  97. BigCodeBench: The Next Generation of HumanEval
  98. From DeepSpeed to FSDP and Back Again with Hugging Face Accelerate
  99. Diffusers welcomes Stable Diffusion 3
  100. Putting RL back in RLHF
  101. Making sense of this mess
  102. Introducing the Hugging Face Embedding Container for Amazon SageMaker
  103. Launching the Artificial Analysis Text to Image Leaderboard & Arena
  104. Introducing NPC-Playground, a 3D playground to interact with LLM-powered NPCs
  105. Faster assisted generation support for Intel Gaudi
  106. Space secrets security update
  107. Benchmarking Text Generation Inference
  108. Training and Finetuning Embedding Models with Sentence Transformers
  109. Falcon 2: An 11B parameter pretrained language model and VLM, trained on over 5000B tokens and 11 languages
  110. CyberSecEval 2 - A Comprehensive Evaluation Framework for Cybersecurity Risks and Capabilities of Large Language Models
  111. Deploy models on AWS Inferentia2 from Hugging Face
  112. Introducing Spaces Dev Mode for a seamless developer experience
  113. Build AI on premise with Dell Enterprise Hub
  114. Hugging Face on AMD Instinct MI300 GPU
  115. From cloud to developers: Hugging Face and Microsoft Deepen Collaboration
  116. Unlocking Longer Generation with Key-Value Cache Quantization
  117. PaliGemma – Google's Cutting-Edge Open Vision Language Model
  118. Hugging Face x LangChain : A new partner package
  119. Introducing the Open Arabic LLM Leaderboard
  120. License to Call: Introducing Transformers Agents 2.0
  121. Subscribe to Enterprise Hub with your AWS Account
  122. Building Cost-Efficient Enterprise RAG applications with Intel Gaudi 2 and Intel Xeon
  123. Introducing the Open Leaderboard for Hebrew LLMs!
  124. Bringing the Artificial Analysis LLM Performance Leaderboard to Hugging Face
  125. Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints
  126. Improving Prompt Consistency with Structured Generations
  127. StarCoder2-Instruct: Fully Transparent and Permissive Self-Alignment for Code Generation
  128. Introducing the Open Chain of Thought Leaderboard
  129. Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent
  130. The Open Medical-LLM Leaderboard: Benchmarking Large Language Models in Healthcare
  131. Welcome Llama 3 - Meta's new open LLM
  132. AI Apps in a Flash with Gradio's Reload Mode
  133. Introducing the LiveCodeBench Leaderboard - Holistic and Contamination-Free Evaluation of Code LLMs
  134. Running Privacy-Preserving Inferences on Hugging Face Endpoints
  135. Ryght’s Journey to Empower Healthcare and Life Sciences with Expert Support from Hugging Face
  136. Introducing Idefics2: A Powerful 8B Vision-Language Model for the community
  137. Vision Language Models Explained
  138. Making thousands of open LLMs bloom in the Vertex AI Model Garden
  139. CodeGemma - an official Google release for code LLMs
  140. Public Policy at Hugging Face
  141. Hugging Face partners with Wiz Research to Improve AI Security
  142. Text2SQL using Hugging Face Dataset Viewer API and Motherduck DuckDB-NSQL-7B
  143. Blazing Fast SetFit Inference with 🤗 Optimum Intel on Xeon
  144. Bringing serverless GPU inference to Hugging Face users
  145. Pollen-Vision: Unified interface for Zero-Shot vision models in robotics
  146. Total noob’s intro to Hugging Face Transformers
  147. Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval
  148. Introducing the Chatbot Guardrails Arena
  149. A Chatbot on your Laptop: Phi-2 on Intel Meteor Lake
  150. Cosmopedia: how to create large-scale synthetic data for pre-training Large Language Models
  151. GaLore: Advancing Large Model Training on Consumer-grade Hardware
  152. Easily Train Models with H100 GPUs on NVIDIA DGX Cloud
  153. Quanto: a PyTorch quantization backend for Optimum
  154. CPU Optimized Embeddings with 🤗 Optimum Intel and fastRAG
  155. Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset
  156. Introducing ConTextual: How well can your Multimodal model jointly reason over text and image in text-rich scenes?
  157. Data is better together: Enabling communities to collectively build better datasets together using Argilla and Hugging Face Spaces
  158. Text-Generation Pipeline on Intel® Gaudi® 2 AI Accelerator
  159. StarCoder2 and The Stack v2
  160. TTS Arena: Benchmarking Text-to-Speech Models in the Wild
  161. AI Watermarking 101: Tools and Techniques
  162. Fine-Tuning Gemma Models in Hugging Face
  163. Introducing the Red-Teaming Resistance Leaderboard
  164. 🪆 Introduction to Matryoshka Embedding Models
  165. Welcome Gemma - Google’s new open LLM
  166. Introducing the Open Ko-LLM Leaderboard: Leading the Korean LLM Evaluation Ecosystem
  167. 🤗 PEFT welcomes new merging methods
  168. Synthetic data: save money, time and carbon with open source
  169. AMD Pervasive AI Developer Contest!
  170. From OpenAI to Open LLMs with Messages API on Hugging Face
  171. SegMoE: Segmind Mixture of Diffusion Experts
  172. NPHardEval Leaderboard: Unveiling the Reasoning Abilities of Large Language Models through Complexity Classes and Dynamic Updates
  173. Constitutional AI with Open LLMs
  174. Hugging Face Text Generation Inference available for AWS Inferentia2
  175. Patch Time Series Transformer in Hugging Face
  176. Introducing the Enterprise Scenarios Leaderboard: a Leaderboard for Real World Use Cases
  177. Accelerate StarCoder with 🤗 Optimum Intel on Xeon: Q8/Q4 and Speculative Decoding
  178. The Hallucinations Leaderboard, an Open Effort to Measure Hallucinations in Large Language Models
  179. An Introduction to AI Secure LLM Safety Leaderboard
  180. Hugging Face and Google partner for open AI collaboration
  181. Open-source LLMs as LangChain Agents
  182. Fine-Tune W2V2-Bert for low-resource ASR with 🤗 Transformers
  183. PatchTSMixer in HuggingFace
  184. Preference Tuning LLMs with Direct Preference Optimization Methods
  185. Accelerating SD Turbo and SDXL Turbo Inference with ONNX Runtime and Olive
  186. Run ComfyUI workflows for free with Gradio on Hugging Face Spaces
  187. A guide to setting up your own Hugging Face leaderboard: an end-to-end example with Vectara's hallucination leaderboard
  188. Make LLM Fine-tuning 2x faster with Unsloth and 🤗 TRL
  189. Welcome aMUSEd: Efficient Text-to-Image Generation
  190. LoRA training scripts of the world, unite!

2023 153

  1. Speculative Decoding for 2x Faster Whisper Inference
  2. 2023, year of open LLMs
  3. Welcome Mixtral - a SOTA Mixture of Experts on Hugging Face
  4. Mixture of Experts Explained
  5. SetFitABSA: Few-Shot Aspect Based Sentiment Analysis using SetFit
  6. AMD + 🤗: Large Language Models Out-of-the-Box Acceleration with AMD GPU
  7. Optimum-NVIDIA Unlocking blazingly fast LLM inference in just 1 line of code
  8. Goodbye cold boot - how we made LoRA Inference 300% faster
  9. Open LLM Leaderboard: DROP deep dive
  10. SDXL in 4 steps with Latent Consistency LoRAs
  11. Make your llama generation time fly with AWS Inferentia2
  12. Introducing Prodigy-HF: a direct integration with Hugging Face
  13. Comparing the Performance of LLMs: A Deep Dive into Roberta, Llama 2, and Mistral for Disaster Tweets Analysis with Lora
  14. Introducing Storage Regions on the HF Hub
  15. Personal Copilot: Train Your Own Coding Assistant
  16. Interactively explore your Huggingface dataset with one line of code
  17. Deploy Embedding Models with Hugging Face Inference Endpoints
  18. The N Implementation Details of RLHF with PPO
  19. Exploring simple optimizations for SDXL
  20. Gradio-Lite: Serverless Gradio Running Entirely in Your Browser
  21. Accelerating over 130,000 Hugging Face models with ONNX Runtime
  22. 🧨 Accelerating Stable Diffusion XL Inference with JAX on Cloud TPU v5e
  23. Chat Templates: An End to the Silent Performance Killer
  24. Deploying the AI Comic Factory using the Inference API
  25. Ethics and Society Newsletter #5: Hugging Face Goes To Washington and Other Summer 2023 Musings
  26. Finetune Stable Diffusion Models with DDPO via TRL
  27. Non-engineers guide: Train a LLaMA 2 chatbot
  28. Llama 2 on Amazon SageMaker a Benchmark
  29. Inference for PROs
  30. Rocket Money x Hugging Face: Scaling Volatile ML Models in Production​
  31. Introduction to 3D Gaussian Splatting
  32. Object Detection Leaderboard
  33. Optimizing your LLM in production
  34. Introducing Würstchen: Fast Diffusion for Image Generation
  35. Fine-tuning Llama 2 70B using PyTorch FSDP
  36. Overview of natively supported quantization schemes in 🤗 Transformers
  37. SafeCoder vs. Closed-source Code Assistants
  38. Efficient Controllable Generation for SDXL with T2I-Adapters
  39. Spread Your Wings: Falcon 180B is here
  40. Fetch Cuts ML Processing Latency by 50% Using Amazon SageMaker & Hugging Face
  41. AudioLDM 2, but faster ⚡️
  42. Code Llama: Llama 2 learns to code
  43. Deprecation of Git Authentication using password
  44. Making LLMs lighter with AutoGPTQ and transformers
  45. Introducing SafeCoder
  46. Introducing IDEFICS: An Open Reproduction of State-of-the-art Visual Langage Model
  47. Hugging Face Hub on the AWS Marketplace: Pay with your AWS Account
  48. Optimizing Bark using 🤗 Transformers
  49. Deploying Hugging Face Models with BentoML: DeepFloyd IF in Action
  50. Fine-tune Llama 2 with DPO
  51. Releasing Swift Transformers: Run On-Device LLMs in Apple Devices
  52. Deploy MusicGen in no time with Inference Endpoints
  53. Huggy Lingo: Using Machine Learning to Improve Language Metadata on the Hugging Face Hub
  54. Towards Encrypted Large Language Models with FHE
  55. Practical 3D Asset Generation: A Step-by-Step Guide
  56. Open-sourcing Knowledge Distillation Code and Weights of SD-Small and SD-Tiny
  57. Stable Diffusion XL on Mac with Advanced Core ML Quantization
  58. AI Policy @🤗: Open ML Considerations in the EU AI Act
  59. Introducing Agents.js: Give tools to your LLMs using JavaScript
  60. Results of the Open Source AI Game Jam
  61. Happy 1st anniversary 🤗 Diffusers!
  62. Llama 2 is here - get it on Hugging Face
  63. Building an AI WebTV
  64. Open-Source Text Generation & LLM Ecosystem at Hugging Face
  65. Fine-tuning Stable Diffusion models on Intel CPUs
  66. Making ML-powered web games with Transformers.js
  67. Deploy LLMs with Hugging Face Inference Endpoints
  68. Making a web app generator with open ML models
  69. Leveraging Hugging Face for complex generative AI use cases
  70. Accelerating Vision-Language Models: BridgeTower on Habana Gaudi2
  71. Ethics and Society Newsletter #4: Bias in Text-to-Image Models
  72. What's going on with the Open LLM Leaderboard?
  73. Panel on Hugging Face
  74. AI Policy @🤗: Response to the U.S. NTIA's Request for Comment on AI Accountability
  75. Fine-Tune MMS Adapter Models for low-resource ASR
  76. Yes, Transformers are Effective for Time Series Forecasting (+ Autoformer)
  77. Faster Stable Diffusion with Core ML on iPhone, iPad, and Mac
  78. Deploy Livebook notebooks as apps to Hugging Face Spaces
  79. Announcing our new Content Guidelines and Policy
  80. Hugging Face and AMD partner on accelerating state-of-the-art models for CPU and GPU platforms
  81. Can foundation models label data like humans?
  82. The Hugging Face Hub for Galleries, Libraries, Archives and Museums
  83. DuckDB: analyze 50,000+ datasets stored on the Hugging Face Hub
  84. Welcome fastText to the Hugging Face Hub
  85. The Falcon has landed in the Hugging Face ecosystem
  86. AI Speech Recognition in Unity
  87. Announcing the Open Source AI Game Jam 🎮
  88. Introducing the Hugging Face LLM Inference Container for Amazon SageMaker
  89. Introducing BERTopic Integration with the Hugging Face Hub
  90. Optimizing Stable Diffusion for Intel CPUs with NNCF and 🤗 Optimum
  91. Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA
  92. Hugging Face Collaborates with Microsoft to launch Hugging Face Model Catalog on Azure
  93. Hugging Face and IBM partner on watsonx.ai, the next-generation enterprise studio for AI builders
  94. 🐶Safetensors audited as really safe and becoming the default
  95. Instruction-tuning Stable Diffusion with InstructPix2Pix
  96. Large-scale Near-deduplication Behind BigCode
  97. Smaller is better: Q8-Chat, an efficient generative AI experience on Xeon
  98. Hugging Face Selected for the French Data Protection Agency Enhanced Support Program
  99. Run a Chatgpt-like Chatbot on a Single GPU with ROCm
  100. Introducing RWKV - An RNN with the advantages of a transformer
  101. Assisted Generation: a new direction toward low-latency text generation
  102. Creating a Coding Assistant with StarCoder
  103. A Dive into Text-to-Video Models
  104. StarCoder: A State-of-the-Art LLM for Code
  105. How to Install and Use the Hugging Face Unity API
  106. Training a language model with 🤗 Transformers using TensorFlow and TPUs
  107. Running IF with 🧨 diffusers on a Free Tier Google Colab
  108. Databricks ❤️ Hugging Face: up to 40% faster training and tuning of Large Language Models
  109. Introducing HuggingFace blog for Chinese speakers: Fostering Collaboration with the Chinese AI community
  110. How to host a Unity game in a Space
  111. Accelerating Hugging Face Transformers with AWS Inferentia2
  112. Graph Classification with Transformers
  113. Creating Privacy Preserving AI with Substra
  114. Snorkel AI x Hugging Face: unlock foundation models for enterprises
  115. StackLLaMA: A hands-on guide to train LLaMA with RLHF
  116. Ethics and Society Newsletter #3: Ethical Openness at Hugging Face
  117. Fast Inference on Large Language Models: BLOOMZ on Habana Gaudi2 Accelerator
  118. Accelerating Stable Diffusion Inference on Intel CPUs
  119. Federated Learning using Hugging Face and Flower
  120. Train your ControlNet with diffusers
  121. Jupyter X Hugging Face
  122. Multivariate Probabilistic Time Series Forecasting with Informer
  123. Fine-tuning 20B LLMs with RLHF on a 24GB consumer GPU
  124. New ViT and ALIGN Models From Kakao Brain
  125. Using Machine Learning to Aid Survivors and Race through Time
  126. ControlNet in 🧨 Diffusers
  127. Ethical Guidelines for developing the Diffusers library
  128. How Hugging Face Accelerated Development of Witty Works Writing Assistant
  129. Red-Teaming Large Language Models
  130. Swift 🧨Diffusers - Fast Stable Diffusion for Mac
  131. Fetch Consolidates AI Tools and Saves 30% Development Time with Hugging Face on AWS
  132. Hugging Face and AWS partner to make AI more accessible
  133. Zero-shot image-to-text generation with BLIP-2
  134. Why we’re switching to Hugging Face Inference Endpoints, and maybe you should too
  135. Parameter-Efficient Fine-Tuning using 🤗 PEFT
  136. Speech Synthesis, Recognition, and More With SpeechT5
  137. Generating Stories: AI for Game Development #5
  138. Introducing ⚔️ AI vs. AI ⚔️ a deep reinforcement learning multi-agents competition system
  139. Accelerating PyTorch Transformers with Intel Sapphire Rapids - part 2
  140. A Dive into Vision-Language Models
  141. The State of Computer Vision at Hugging Face 🤗
  142. 2D Asset Generation: AI for Game Development #4
  143. Using LoRA for Efficient Stable Diffusion Fine-Tuning
  144. What Makes a Dialog Agent Useful?
  145. Optimum+ONNX Runtime - Easier, Faster training for your Hugging Face models
  146. 3D Asset Generation: AI for Game Development #3
  147. Universal Image Segmentation with Mask2Former and OneFormer
  148. Welcome PaddlePaddle to the Hugging Face Hub
  149. Image Similarity with Hugging Face Datasets and Transformers
  150. AI for Game Development: Creating a Farming Game in 5 Days. Part 2
  151. Introduction to Graph Machine Learning
  152. AI for Game Development: Creating a Farming Game in 5 Days. Part 1
  153. Accelerating PyTorch Transformers with Intel Sapphire Rapids - part 1

2022 116

  1. Zero-shot image segmentation with CLIPSeg
  2. Model Cards
  3. Let's talk about biases in machine learning! Ethics and Society Newsletter #2
  4. A Complete Guide to Audio Datasets
  5. Faster Training and Inference: Habana Gaudi®2 vs Nvidia A100 80GB
  6. Illustrating Reinforcement Learning from Human Feedback (RLHF)
  7. From GPT2 to Stable Diffusion: Hugging Face arrives to the Elixir community
  8. Deep Learning with Proteins
  9. Using Stable Diffusion with Core ML on Apple Silicon
  10. Probabilistic Time Series Forecasting with 🤗 Transformers
  11. VQ-Diffusion
  12. We are hiring interns!
  13. Diffusion Models Live Event
  14. Director of Machine Learning Insights [Part 4]
  15. Accelerating Document AI
  16. An overview of inference solutions on Hugging Face
  17. Hugging Face Machine Learning Demos on arXiv
  18. Sentiment Analysis on Encrypted Data with Homomorphic Encryption
  19. Generating Human-level Text with Contrastive Search in Transformers 🤗
  20. Introducing our new pricing
  21. Training Stable Diffusion with Dreambooth using Diffusers
  22. Fine-Tune Whisper For Multilingual ASR with 🤗 Transformers
  23. Accelerate your models with 🤗 Optimum Intel and OpenVINO
  24. Evaluating Language Model Bias with 🤗 Evaluate
  25. From PyTorch DDP to Accelerate to Trainer, mastery of distributed training with ease
  26. MTEB: Massive Text Embedding Benchmark
  27. Getting Started with Hugging Face Inference Endpoints
  28. 🧨 Stable Diffusion in JAX / Flax !
  29. Optimization story: Bloom inference
  30. Introducing DOI: the Digital Object Identifier to Datasets and Models
  31. Japanese Stable Diffusion
  32. Very Large Language Models and How to Evaluate Them
  33. Image Classification with AutoTrain
  34. How 🤗 Accelerate runs very large models thanks to PyTorch
  35. SetFit: Efficient Few-Shot Learning Without Prompts
  36. Ethics and Society Newsletter #1
  37. Incredibly Fast BLOOM Inference with DeepSpeed and Accelerate
  38. What's new in Diffusers? 🎨
  39. Train your first Decision Transformer
  40. How to train a Language Model with Megatron-LM
  41. OpenRAIL: Towards open and responsible AI licensing frameworks
  42. Visualize proteins on Hugging Face Spaces
  43. Stable Diffusion with 🧨 Diffusers
  44. Pre-Train BERT with Hugging Face Transformers and Habana Gaudi
  45. Deploying 🤗 ViT on Vertex AI
  46. Deep Dive: Vision Transformers On Hugging Face Optimum Graphcore
  47. A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes
  48. Introducing Skops
  49. Hugging Face's TensorFlow Philosophy
  50. Deploying 🤗 ViT on Kubernetes with TF Serving
  51. Train and Fine-Tune Sentence Transformers Models
  52. Proximal Policy Optimization (PPO)
  53. Introducing the Private Hub: A New Way to Build With Machine Learning
  54. Nyströmformer: Approximating self-attention in linear time and memory via the Nyström method
  55. Comments on U.S. National AI Research Resource Interim Report
  56. Introducing new audio and vision documentation in 🤗 Datasets
  57. Faster Text Generation with TensorFlow and XLA
  58. Deploying TensorFlow Vision Models in Hugging Face with TF Serving
  59. Advantage Actor Critic (A2C)
  60. How to train your model dynamically using adversarial data
  61. The Technology Behind BLOOM Training
  62. Building a Playlist Generator with Sentence Transformers
  63. Introducing The World's Largest Open Multilingual Language Model: BLOOM
  64. Getting Started with Sentiment Analysis on Twitter
  65. Policy Gradient with PyTorch
  66. Liftoff! How to get started with your first ML project 🚀
  67. Accelerate Large Model Training using DeepSpeed
  68. Announcing Evaluation on the Hub
  69. Getting Started With Embeddings
  70. Convert Transformers to ONNX with Hugging Face Optimum
  71. Intel and Hugging Face Partner to Democratize Machine Learning Hardware Acceleration
  72. Director of Machine Learning Insights [Part 3: Finance Edition]
  73. The Annotated Diffusion Model
  74. Deep Q-Learning with Space Invaders
  75. Graphcore and Hugging Face Launch New Lineup of IPU-Ready Transformers
  76. Introducing Pull Requests and Discussions 🥳
  77. Efficient Table Pre-training without Real Data: An Introduction to TAPEX
  78. An Introduction to Q-Learning Part 2/2
  79. How Sempre Health is leveraging the Expert Acceleration Program to accelerate their ML roadmap
  80. Putting ethical principles at the core of the research lifecycle
  81. An Introduction to Q-Learning Part 1
  82. Machine Learning Experts - Sasha Luccioni
  83. Announcing the Hugging Face Fellowship Program
  84. Gradio 3.0 is Out!
  85. Director of Machine Learning Insights [Part 2: SaaS Edition]
  86. Student Ambassador Program’s call for applications is open!
  87. Accelerated Inference with Optimum and Transformers Pipelines
  88. We Raised $100 Million for Open & Collaborative Machine Learning 🚀
  89. Welcome fastai to the Hugging Face Hub
  90. An Introduction to Deep Reinforcement Learning
  91. Accelerate Large Model Training using PyTorch Fully Sharded Data Parallel
  92. Opinion Classification with Kili and HuggingFace AutoTrain
  93. Director of Machine Learning Insights
  94. Getting Started with Transformers on Habana Gaudi
  95. Introducing Hugging Face for Education 🤗
  96. Supercharged Customer Service with Machine Learning
  97. CO2 Emissions and the 🤗 Hub: Leading the Charge
  98. Machine Learning Experts - Lewis Tunstall
  99. Habana Labs and Hugging Face Partner to Accelerate Transformer Model Training
  100. ~Don't~ Repeat Yourself
  101. Introducing Decision Transformers on Hugging Face 🤗
  102. Machine Learning Experts - Margaret Mitchell
  103. Announcing the 🤗 AI Research Residency Program
  104. Fine-Tune a Semantic Segmentation Model with a Custom Dataset
  105. Accelerate BERT inference with Hugging Face Transformers and AWS Inferentia
  106. Image search with 🤗 datasets
  107. Guiding Text Generation with Constrained Beam Search in 🤗 Transformers
  108. BERT 101 - State Of The Art NLP Model Explained
  109. Fine-Tune ViT for Image Classification with 🤗 Transformers
  110. Getting Started with Sentiment Analysis using Python
  111. Making automatic speech recognition work on large files with Wav2Vec2 in 🤗 Transformers
  112. Supercharged Searching on the 🤗 Hub
  113. Welcome Stable-baselines3 to the Hugging Face Hub 🤗
  114. Case Study: Millisecond Latency using Hugging Face Infinity and modern CPUs
  115. Boosting Wav2Vec2 with n-grams in 🤗 Transformers
  116. Deploy GPT-J 6B for inference using Hugging Face Transformers and Amazon SageMaker

2021 40

  1. Active Learning with AutoNLP and Prodigy
  2. Gradio is joining Hugging Face!
  3. Perceiver IO: a scalable, fully-attentional model that works on any modality
  4. Training CodeParrot 🦜 from Scratch
  5. Introducing Snowball Fight ☃️, our first ML-Agents environment
  6. Getting Started with Hugging Face Transformers for IPUs with Optimum
  7. Introducing the Data Measurements Tool: an Interactive Tool for Looking at Datasets
  8. Accelerating PyTorch distributed fine-tuning with Intel technologies
  9. Fine-Tune XLSR-Wav2Vec2 for low-resource ASR with 🤗 Transformers
  10. Scaling up BERT-like model Inference on modern CPU - Part 2
  11. Course Launch Community Event
  12. Large Language Models: A New Moore's Law?
  13. Train a Sentence Embedding Model with 1B Training Pairs
  14. The Age of Machine Learning As Code Has Arrived
  15. Fine tuning CLIP with Remote Sensing (Satellite) images and captions
  16. Hosting your Models and Datasets on Hugging Face Spaces using Streamlit
  17. Showcase Your Projects in Spaces using Gradio
  18. Summer at Hugging Face
  19. Hugging Face and Graphcore partner for IPU-optimized Transformers
  20. Introducing Optimum: The Optimization Toolkit for Transformers at Scale
  21. Deep Learning over the Internet: Training Language Models Collaboratively
  22. Welcome spaCy to the Hugging Face Hub
  23. Deploy Hugging Face models easily with Amazon SageMaker
  24. Sentence Transformers in the Hugging Face Hub
  25. Few-shot learning in practice: GPT-Neo and the 🤗 Accelerated Inference API
  26. Using & Mixing Hugging Face Models with Gradio 2.0
  27. Scaling-up BERT Inference on CPU (Part 1)
  28. Introducing 🤗 Accelerate
  29. Distributed Training: Train BART/T5 for Summarization using 🤗 Transformers and Amazon SageMaker
  30. Understanding BigBird's Block Sparse Attention
  31. The Partnership: Amazon SageMaker and Hugging Face
  32. My Journey to a serverless transformers pipeline on Google Cloud
  33. Fine-Tune Wav2Vec2 for English ASR in Hugging Face with 🤗 Transformers
  34. Hugging Face Reads, Feb. 2021 - Long-range Transformers
  35. Simple considerations for simple people building fancy neural networks
  36. Retrieval Augmented Generation with Huggingface Transformers and Ray
  37. Hugging Face on PyTorch / XLA TPUs
  38. Faster TensorFlow models in Hugging Face Transformers
  39. Fit More and Train Faster With ZeRO via DeepSpeed and FairScale
  40. How we sped up transformer inference 100x for 🤗 API customers

2020 8

  1. Leveraging Pre-trained Language Model Checkpoints for Encoder-Decoder Models
  2. Porting fairseq wmt19 translation system to transformers
  3. Hyperparameter Search with Transformers and Ray Tune
  4. Transformer-based Encoder-Decoder Models
  5. Block Sparse Matrices for Smaller and Faster Language Models
  6. The Reformer - Pushing the limits of language modeling
  7. How to generate text: using different decoding methods for language generation with Transformers
  8. How to train a new language model from scratch using Transformers and Tokenizers

Undated 1

  1. IsValorum