LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family
•
56
Community Blog & Articles
Community Articles
view all
llmreasoningagents
DeepMath: A lightweight math reasoning Agent with smolagents
36
December 4, 2025
llmfine-tuningopen-source
Hot
We Got Claude to Fine-Tune an Open Source LLM
581
December 4, 2025
transformersv5community
Hot
Transformers v5: Simple model definitions powering the AI ecosystem
277
December 1, 2025
diffusersfluxquantization
Diffusers welcomes FLUX-2
- +4
170
November 25, 2025
transformerspytorchoptimization
Hot
Continuous batching from first principles
310
November 25, 2025
Building Deep Research: How we Achieved State of the Art
34
November 24, 2025
OVHcloud on Hugging Face Inference Providers 🔥
76
November 24, 2025
llmexperimentationfine-tuning
20x Faster TRL Fine-tuning with RapidFire AI
26
November 21, 2025
audiospeechleaderboard
Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracks
24
November 21, 2025
llmcoremlmlx
Introducing AnyLanguageModel: One API for Local and Remote LLMs on Apple Platforms
38
November 20, 2025
Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models
34
November 19, 2025
amdrocmkernels
Easily Build and Share ROCm Kernels with Hugging Face
36
November 17, 2025
Join the AMD Open Robotics Hackathon
13
November 13, 2025
partnershipsgoogleannouncement
Building for an Open Future - our new partnership with Google Cloud
46
November 13, 2025
NEW
Articles from
Team
or
Enterprise organizations will get promoted to the main section.
LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family
•
56
🪄 Interpreto: A Unified Toolkit for Interpretability of Transformer Models
•
32
New in llama.cpp: Anthropic Messages API
•
31
One Year Since the “DeepSeek Moment”
•
28
How We Built a Semantic Highlight Model To Save Token Cost for RAG
•
59
Introducing OptiMind, a research model designed for optimization
•
31
Challenges of Synthetic Dataset Generation
•
10
LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR
•
70
Scaling OpenEnv: From Free Usage to Thousands of Concurrent Environments
•
8
Scaling Real-Time Voice Agents with Cache-Aware Streaming ASR
•
67
Optimizing GLM4-MoE for Production: 65% Faster TTFT with SGLang
•
7
VLM-OCR Recipes on GPU Infrastructure
•
11
Security, Governance and Performance for Dell On-Prem AI Builders
•
6
Benchmark Smarter: Tailor Your Model Evaluation Suite with EvalScope
•
6
Code a simple RAG from scratch
•
283
From GRPO to DAPO and GSPO: What, Why, and How
•
78
Make and publish your Reachy Mini App
•
33
RexRerankers: SOTA Rankers for Product Discovery and AI Assistants
•
4
“DeepSeek R1 时刻” 一周年
•
4
Reverse Engineering a $500M Mystery: From HashHop to Memory-Augmented Language Models
•
4