Hugging Face's logo

Blog, Articles, and discussions

SmolVLM Grows Smaller – Introducing the 250M & 500M Models!

By  andito January 23, 2025 • 54

Community Articles
view all

Hugging Face and FriendliAI partner to supercharge model deployment on the Hub

By  ajshinfai January 22, 2025 • 28

Timm ❤️ Transformers: Use any timm model with transformers

By  ariG23498 January 16, 2025 • 33

Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference

By  mfuntowicz January 16, 2025 • 59

Train 400x faster Static Embedding Models with Sentence Transformers

By  tomaarsen January 15, 2025 • 120

Run ComfyUI workflows for free on Spaces

By  multimodalart January 14, 2024 • 40

AI Agents Are Here. What Now?

By  meg January 13, 2025 • 52

Visual Document Retrieval Goes Multilingual

By  marco January 10, 2025 guest • 61

CO₂ Emissions and Models Performance: Insights from the Open LLM Leaderboard

By  alozowski January 9, 2025 • 14

Introducing smolagents: simple agents that write actions in code.

By  m-ric December 31, 2024 • 519

Visualize and understand GPU memory in PyTorch

By  qgallouedec December 24, 2024 • 170

Controlling Language Model Generation with NVIDIA's LogitsProcessorZoo

By  ariG23498 December 23, 2024 • 36

Evaluating Audio Reasoning with Big Bench Audio

By  mhillsmith December 20, 2024 guest • 17

Finally, a Replacement for BERT: Introducing ModernBERT

By  bwarner December 19, 2024 guest • 499

Bamba: Inference-Efficient Hybrid Mamba2 Model

By  Linsong-C December 18, 2024 guest • 40