Per-tensor layout maps for GGUF quantization
bartowski
• • 33Community Blog & Articles
Community Articles
view all
llmrltrl
Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL
19
September 10, 2026 
gradioworkflowsautomatic1111
Rebuilding AUTOMATIC1111 with Gradio Workflow
41
September 10, 2026 
IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license
52
September 9, 2026 
Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic
18
September 8, 2026 
NeoMME: an efficient Multimodal-native and Multilingual Encoder
99
September 3, 2026 
nlpguidecommunity
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
108
September 3, 2026 
agentsopen-sourcedatasets
Give Your Coding Agents a Memory You Own
87
September 3, 2026 
rlgrpotrl
Training a coding model to paint watercolours with TRL and OpenEnv
67
September 3, 2026 
BenchMIRT: What are LLM benchmarks actually measuring?
22
September 1, 2026 
inferencejavascriptwebgpu
Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI
68
September 1, 2026 
audiospeechleaderboard
The Open ASR Leaderboard Adds Its First Global South Language
- +6
56
August 28, 2026 
nlpguidecommunity
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
129
August 26, 2026 
Granite 4.2 LLMs: How They're Built
111
August 25, 2026 
Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original
56
August 25, 2026 NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Per-tensor layout maps for GGUF quantization
bartowski
• • 33Making open-source AI weather forecasting models easy to run
hugging-science
• • 30Same bytes, closer to the original: two lines of AutoRound we had wrong
FINAL-Bench
• • 12TranslatePsy-AfriSLM: Optimized Machine Translation for African Languages
qvac
• • 14KV Caching Explained: Optimizing Transformer Inference Efficiency
not-lain
• • 413Real-Time Intelligence with IBM Time Series Models on Confluent
ibm-research
• • 52How Did We Get Here?
NILKNARFGonzo
• • 7One sandbox per rollout, or how labs run RL for agents in 2026
sergiopaniego
• • 6Was sind KI-Agenten? So funktioniert Agentic AI
Agenten
• • 6Trained 210M text-to-image model from scratch on one GPU: what actually mattered
ivanmikhnenkov
• • 6So, let’s make our own dataset
tegridydev
• • 5Uncensor any LLM with abliteration
mlabonne
• • 918Open Yap 1K: 1,000 hours of full-duplex natural conversation, free for commercial use
TheAgenticDataCompany
• • 13Lorem Ipsum
GGUFGuy
• • 4Mastering Tensor Dimensions in Transformers
not-lain
• • 204A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond
karina-zadorozhny
• • 48DAVIDAU DELETED MY POST AND BANNED ME FOR ASKING ABOUT BENCHMARKS — HERE IS THE FULL ANALYSIS (9B + 27B + 390 MODELS)
DedeProGames
• • 19New imatrix dataset
bartowski
• • 17Code a simple RAG from scratch
ngxson
• • 384Decoding Strategies in Large Language Models
mlabonne
• • 119