The Fast Gemma Challenge: our verified-SOTA recipe, in full
FINAL-Bench
• • 24Community Blog & Articles
Community Articles
view all
amdrocmkernels
Easily Build and Share ROCm Kernels with Hugging Face
38
November 17, 2025 
Join the AMD Open Robotics Hackathon
16
November 13, 2025 
partnershipsgoogleannouncement
Building for an Open Future - our new partnership with Google Cloud
48
November 13, 2025 Aligning to What? Rethinking Agent Generalization in MiniMax M2
43
October 30, 2025 On the Shifting Global Compute Landscape
62
October 29, 2025 
lerobotrobotics
Building a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac
33
October 29, 2025 How to Build a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac for Healthcare
20
October 28, 2025 
Granite 4.0 Nano: Just how small can you go?
126
October 28, 2025 
ethicsguidespeech
Voice Cloning with Consent
43
October 28, 2025 
datasetsxethub
Streaming datasets: 100x More Efficient
- +1
87
October 27, 2025 
huggingface_hubpythonannouncement
huggingface_hub v1.0: Five Years of Building the Foundation of Open Machine Learning
76
October 27, 2025 
lerobotrobotics
LeRobot v0.4.0: Supercharging OSS Robot Learning
- +5
50
October 24, 2025 
announcementopen-sourcecommunity
Building the Open Agent Ecosystem Together: Introducing OpenEnv
- +6
166
October 23, 2025 
hubpartnershipssecurity
Hugging Face and VirusTotal collaborate to strengthen AI security
55
October 22, 2025 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
The Fast Gemma Challenge: our verified-SOTA recipe, in full
FINAL-Bench
• • 24Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv
sergiopaniego
• • 19Lattice: an 8 MB static retriever that embeds Wikipedia in 7 minutes
erikkaum
• • 18Model Genome: Fingerprinting Whether an LLM Was Trained From Scratch or Derived
mayafree
• • 12LFM2.5-Encoders for Fast Long-Context Inference on CPU
LiquidAI
• • 68超越表层对齐：信念是通往深层对齐的新入口
Alibaba-VELLDEPTH
• • 9mDenseOn with the mLateOn: Open Multilingual, Long-Context, and Code Retrieval Models
lightonai
• • 34Uncensor any LLM with abliteration
mlabonne
• • 891The OlmoEarth Platform: Geospatial inference at planetary scale
allenai
• • 40Bekko Embedding: how small can a multilingual retrieval model be?
hotchpotch
• • 6Language Identification for 42 Indian Languages: Opening New Frontiers in Indic Speech AI
ARTPARK-IISc
• • 6jina-reranker-v3.5: Faster Listwise Reranking with Hybrid Attention and Self-Distillation
jinaai
• • 6GLInt: Geometry-Matched Hard Negatives for Late-Interaction Retrieval
chungimungi
• • 6Rebuilding Among AIs from Six Log Files
DedeProGames
• • 6Code a simple RAG from scratch
ngxson
• • 376KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 390Kimi K3 Model Overview: 2.8T Parameters, MXFP4 Quantization, and What the Open Weights Mean for the Community
ResterChed
• • 195FLUX 3 Model Overview: Multimodal Flow Models for Image, Video, Audio, and Action Prediction
ResterChed
• • 14Optimum Intel v2.1.0
echarlaix
• • 5Using OCR models with llama.cpp
ggml-org
• • 39