NEO-unify: Building Native Multimodal Unified Models End to End
•
82
Community Blog & Articles
Community Articles
view all
Mini-R1: Reproduce Deepseek R1 „aha moment“ a RL tutorial
51
January 31, 2025 
diffusersaiartai art
The AI tools for Art Newsletter - Issue 1
84
January 31, 2025 
awspartnerships
How to deploy and fine-tune DeepSeek models on AWS
55
January 30, 2025 
announcementhubinference-providers
HotWelcome to Inference Providers on the Hub 🔥
- +3
494
January 28, 2025 
llmsreasoningresearch
HotOpen-R1: a fully open reproduction of DeepSeek-R1
889
January 28, 2025 
diffusersguidevideo_gen
State of open video generation models in Diffusers
67
January 27, 2025 
agentssmolagentsmultimodal
We now support VLMs in smolagents!
112
January 24, 2025 Mastering Long Contexts in LLMs with KVPress
73
January 23, 2025 
multimodalvlmvision
SmolVLM Grows Smaller – Introducing the 256M & 500M Models!
192
January 23, 2025 
partnershipsfriendliaimodel-deployment
Hugging Face and FriendliAI partner to supercharge model deployment on the Hub
36
January 22, 2025 Yay! Organizations can now publish blog Articles
53
January 20, 2025 
timmcvcommunity
Timm ❤️ Transformers: Use any timm model with transformers
- +1
54
January 16, 2025 
tgibackendsvllm
Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference
76
January 16, 2025 
nlpguidecommunity
HotTrain 400x faster Static Embedding Models with Sentence Transformers
227
January 15, 2025 NEW
Articles from
Team
or
Enterprise organizations will get promoted to the main section.
NEO-unify: Building Native Multimodal Unified Models End to End
•
82
🏟️ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do
•
33
MARL: Runtime Middleware That Reduces LLM Hallucination Without Fine-Tuning
•
14
The ML Engineer's Guide to Protein AI
•
25
TiRex on the Edge
•
12
Structural Problems in AI Benchmarking and the Case for a Unified Evaluation Framework
•
12
How NVIDIA Builds Open Data for AI
•
11
Uncensor any LLM with abliteration
•
799
Building Tucano 2: Open-Source Language Models That Actually _Think_ in Portuguese
•
8
From GRPO to DAPO and GSPO: What, Why, and How
•
100
Konkani LLM: Bringing a Multi-Script Low-Resource Language to the AI Era
•
7
We’re open-sourcing our text-to-image model and the process behind it
•
94
Deploying Open Source Vision Language Models (VLM) on Jetson
•
34
Kanon 2 Reranker: the most powerful reranker for legal RAG
•
6
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
241
Forge: Scalable Agent RL Framework and Algorithm
•
137
Code a simple RAG from scratch
•
306
OpenMed: Six Months of Open-Source Medical AI and the Road Ahead
•
18
ShopRLVE-GYM: Adaptive Verifiable Environments for E-Commerce Conversational Agents
•
4
Text-to-image Architectural Experiments
•
54