Community Blog & Articles

Community Articles

Your Inference Server is Secretly a Learner: Reef Infrastructure for Continual Self-Improving Agents

IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license

BananaMind 2 Pro: We've (almost) matched SmolLM2 at 20x fewer tokens... Trained On a 5070 Ti

One sandbox per rollout, or how labs run RL for agents in 2026

Per-tensor layout maps for GGUF quantization

KV Caching Explained: Optimizing Transformer Inference Efficiency

Layer-Feedback Transformer (LFT)

Deploy local agents everywhere with LFM2.5-2.6B

DAVIDAU DELETED MY POST AND BANNED ME FOR ASKING ABOUT BENCHMARKS — HERE IS THE FULL ANALYSIS (9B + 27B + 390 MODELS)

When Benchmark Numbers Become Marketing

Optimum-Intel v2.2.0 & OpenVINO GenAI 2026.4.0: What's New

Extremely Fast and Accurate Transcription with Granite Speech 5.0 Turbo CTC

Your Agent Aced the Task. Will It Do It Again?

September 15, 2026

llmrltrl

Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL

September 10, 2026

gradioworkflowsautomatic1111

Rebuilding AUTOMATIC1111 with Gradio Workflow

September 10, 2026

Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic

September 8, 2026

NeoMME: an efficient Multimodal-native and Multilingual Encoder

108

September 3, 2026

nlpguidecommunity

Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps

128

September 3, 2026

agentsopen-sourcedatasets

Give Your Coding Agents a Memory You Own

113

September 3, 2026

rlgrpotrl

Training a coding model to paint watercolours with TRL and OpenEnv

September 3, 2026

BenchMIRT: What are LLM benchmarks actually measuring?

September 1, 2026

inferencejavascriptwebgpu

Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI

September 1, 2026

audiospeechleaderboard

The Open ASR Leaderboard Adds Its First Global South Language

August 28, 2026

nlpguidecommunity

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

141

August 26, 2026

Granite 4.2 LLMs: How They're Built

121

August 25, 2026

Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original

August 25, 2026

Community Articles

NEW Articles from Team or Enterprise organizations will get promoted to the main section.

What If the Adaptation Were a Model? ShadowPEFT in 🤗 PEFT library

适配器即模型 —— ShadowPEFT 现已集成到 🤗 PEFT 库

Your Inference Server is Secretly a Learner: Reef Infrastructure for Continual Self-Improving Agents

IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license

Same bytes, closer to the original: two lines of AutoRound we had wrong

OpenRouter Leaderboard: 425 Models by Price, Measured Speed and Korean Quality

Inside the JEV Ecosystem: 13 Answer Verifiers on One Test Set

Making open-source AI weather forecasting models easy to run

funes: Local Memory for Coding Agents, Built on Lance

Uncensor any LLM with abliteration

BananaMind 2 Pro: We've (almost) matched SmolLM2 at 20x fewer tokens... Trained On a 5070 Ti

One sandbox per rollout, or how labs run RL for agents in 2026

Per-tensor layout maps for GGUF quantization

KV Caching Explained: Optimizing Transformer Inference Efficiency

Layer-Feedback Transformer (LFT)

Deploy local agents everywhere with LFM2.5-2.6B

DAVIDAU DELETED MY POST AND BANNED ME FOR ASKING ABOUT BENCHMARKS — HERE IS THE FULL ANALYSIS (9B + 27B + 390 MODELS)

When Benchmark Numbers Become Marketing

Optimum-Intel v2.2.0 & OpenVINO GenAI 2026.4.0: What's New

Extremely Fast and Accurate Transcription with Granite Speech 5.0 Turbo CTC