Community Blog & Articles
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
Granite 4.2 LLMs: How They're Built
Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original
Wire It, Run It, Deploy It: AI Workflows in Gradio
How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code
Measuring benchmark optimization in speech recognition
Up to 3.2x Faster Inference with LFM2.5-DSpark
How Much Memory Does Your Agent Actually Need?
Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers
Same Cluster, 33 Points More Utilization: What Changed Was the Order
State of Open Models: Summer 2026 Observations
Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets
What We Learned by Reproducing 2,200 papers from ICML
Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis
NEW Articles from Team or Enterprise organizations will get promoted to the main section. LFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation
LiquidAI
• • 34
Extremely Fast and Accurate Transcription with Granite Speech 5.0 Turbo CTC
ibm-granite
• • 22
Writing Down the Line Between Luck and Skill
FINAL-Bench
• • 12
ArmBench-ASR: A Benchmark for Armenian ASR
Metric-AI
• • 11
We changed one line and the benchmark score moved 0.21 AUROC
FINAL-Bench
• • 10
mLateOn: A New SoTA for Multilingual ColBERT-Style Retrieval, Evaluated on HAKARI-Bench
hotchpotch
• • 8
Introducing the EdgeFirst Model Zoo
EdgeFirst
• • 7
VLM Run Gateway: Run GLM-OCR, DeepSeek-OCR-2, dots.mocr with an OpenAI Compatible API
Sleeper Agents and How to Tame Them
tngtech
• • 26
Uncensor any LLM with abliteration
mlabonne
• • 901
Agentic RL: Token-In, Token-Out Done Right
huggingface
• • 29
Fine-Tune SraVaani on Your Own Speech Data
ARTPARK-IISc
• • 6
LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge
LiquidAI
• • 49
Modern LLMs: What the FLIP is an Engram!?
Blackroot
• • 4
Code a simple RAG from scratch
ngxson
• • 383
Norm-Preserving Biprojected Abliteration
grimjim
• • 94
NEO-unify: Building Native Multimodal Unified Models End to End
FLUX 3 Model Overview: Multimodal Flow Models for Image, Video, Audio, and Action Prediction
Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model
CohereLabs
• • 38
Exploring NVIDIA Nemotron 3.5 Lightning: Making it see with little resources
tngtech
• • 17