26M 파라미터 기반 초경량 Tool Calling 전용 모델 Needle의 효율적 아키텍처
Needle and the Return of the Tiny Specialist Model
Needle and the Return of the Tiny Specialist Model
99M Parameters 기반 31개 언어 지원 초경량 On-device TTS 구현
Building an AI Tutor for 40 Million Ethiopian Students Who Learn in Amharic
I Built an AI That Detects Pet Stress From Photos — Here's the Stack
How low-bit inference enables efficient AI
Granite 4.0 Nano: Just how small can you go?
Get your VLM running in 3 simple steps on Intel CPUs
Accelerate ND-Parallel: A guide to Efficient Multi-GPU Training
Blazingly fast whisper transcriptions with Inference Endpoints
🚀 Accelerating LLM Inference with TGI on Intel Gaudi
State of open video generation models in Diffusers
Train 400x faster Static Embedding Models with Sentence Transformers
Diffusers welcomes Stable Diffusion 3.5 Large
Welcome Gemma 2 - Google’s new open LLM
Falcon 2: An 11B parameter pretrained language model and VLM, trained on over 5000B tokens and 11 languages
Deploy models on AWS Inferentia2 from Hugging Face
Quanto: a PyTorch quantization backend for Optimum
Accelerating over 130,000 Hugging Face models with ONNX Runtime
Overview of natively supported quantization schemes in 🤗 Transformers
Efficient Controllable Generation for SDXL with T2I-Adapters