HU
Hugging Face
3 stories this week · 10 topics · huggingface.co
Hugging Face's blog: open-source models, libraries and hands-on ML tutorials.
Latest from Hugging Face
- Machine LearningIBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license2 days ago
- Image GenerationRebuilding AUTOMATIC1111 with Gradio Workflow1 day ago
- AI ResearchSafety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic3 days ago
- Machine LearningNeoMME: an efficient Multimodal-native and Multilingual Encoder8 days ago
- Machine LearningFine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps8 days ago
- DevGive Your Coding Agents a Memory You Own8 days ago
- Machine LearningTraining a coding model to paint watercolours with TRL and OpenEnv8 days ago
- Machine LearningReal-Time Intelligence with IBM Time Series Models on Confluent 9 days ago
- LLM & Text GenerationBenchMIRT: What are LLM benchmarks actually measuring?9 days ago
- DevIntroducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI10 days ago
- Machine LearningThe Open ASR Leaderboard Adds Its First Global South Language14 days ago
- Machine LearningTraining and Finetuning Multi-Vector Embedding Models with Sentence Transformers16 days ago
- LLM & Text GenerationQuantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original17 days ago
- DevWire It, Run It, Deploy It: AI Workflows in Gradio17 days ago
- Machine LearningUp to 3.2x Faster Inference with LFM2.5-DSpark21 days ago
- Machine LearningMeasuring benchmark optimization in speech recognition21 days ago
- Machine LearningLFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation23 days ago
- AgentsHow Much Memory Does Your Agent Actually Need?23 days ago
- Machine LearningMulti-Vector (Late Interaction) Embedding Models with Sentence Transformers24 days ago
- Chips & ComputeSame Cluster, 33 Points More Utilization: What Changed Was the Order24 days ago
- Computer VisionLFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge30 days ago
- Machine LearningIntroducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis29 days ago
- AgentsThinking of ACE? We Can Do It with Fewer TokensAug 11, 2026
- Machine LearningBuild Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTSAug 10, 2026
- Machine LearningMaking Knowledge Distillation Cheap Enough to Run at ScaleAug 10, 2026
- Machine LearningMeta is back with Muse Glimmer: local, agentic, multimodal, and open sourceAug 10, 2026
- EducationTutorMoments: Do AI tutors know when to help and when to hold back?Aug 7, 2026
- DevBaseten on Hugging Face Inference Providers 🔥Aug 6, 2026
- AgentsDeploy local agents everywhere with LFM2.5-2.6BAug 4, 2026
- Chips & ComputeGPU Management: Why Idle GPUs Are the New Grounded AircraftJul 30, 2026