Community Blog & Articles

Community Articles

Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model

Deploy local agents everywhere with LFM2.5-2.6B

TutorMoments: Do AI tutors know when to help and when to hold back?

FineBooks: are open OCR models good enough to unlock historical knowledge?

Lattice: an 8 MB static retriever that embeds Wikipedia in 7 minutes

Sleeper Agents and How to Tame Them

Model Genome: Fingerprinting Whether an LLM Was Trained From Scratch or Derived

Exploring NVIDIA Nemotron 3.5 Lightning: Making it see with little resources

AX-Ray, Finding Causal-Leakage Defects in Two General-Purpose Public Models

about 11 hours ago

Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv

GLInt: Geometry-Matched Hard Negatives for Late-Interaction Retrieval

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

Extreme Overtraining in Tiny Language Models

Rebuilding Among AIs from Six Log Files

On the integrity of the Arabic TTS Arena leaderboard

Beyond the Aggregate Score: Per-Country Domain Shift in the GWHD Wheat Head Detection Model Zoo

Uncensor any LLM with abliteration

Day-0 Muse Glimmer Support on Intel Platforms with vLLM and Hugging Face

Mastering Tensor Dimensions in Transformers

Luth-2: Pushing the French Capabilities of SLMs with MOPD

ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration

Why Specialization Is Inevitable

evaluationcommunityleaderboard

Featuring Every Eval Ever Results on Hugging Face Model Pages

+3

DiScoFormer: One transformer for density and score, across distributions

guidevllminference

Run a vLLM Server on HF Jobs in One Command

Accelerating Transformers Fine-Tuning with NVIDIA NeMo AutoModel

audiospeechleaderboard

Introducing the FFASR Leaderboard: Benchmarking ASR in the Real World

+1

cihuggingface_hubagents

Shipping huggingface_hub every week with AI, open tools, and a human in the loop

cross-origin-storagecosannouncement

Experimenting with the proposed Cross-Origin Storage API in Transformers.js

PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters

guideopen-source-collab

We got local models to triage the OpenClaw repo for FREE!*

MosaicLeaks: Can your research agent keep a secret?

Beyond LoRA: Can you beat the most popular fine-tuning technique?

agentstransformersevaluation

Is it agentic enough? Benchmarking open models on your own tooling

Community Articles

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

Meet North Micro Vision: A 2.4B Native-Resolution Vision-Language Model

Deploy local agents everywhere with LFM2.5-2.6B

TutorMoments: Do AI tutors know when to help and when to hold back?

FineBooks: are open OCR models good enough to unlock historical knowledge?

Lattice: an 8 MB static retriever that embeds Wikipedia in 7 minutes

Sleeper Agents and How to Tame Them

Model Genome: Fingerprinting Whether an LLM Was Trained From Scratch or Derived

Exploring NVIDIA Nemotron 3.5 Lightning: Making it see with little resources

AX-Ray, Finding Causal-Leakage Defects in Two General-Purpose Public Models

about 11 hours ago

Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv

GLInt: Geometry-Matched Hard Negatives for Late-Interaction Retrieval

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

Extreme Overtraining in Tiny Language Models

Rebuilding Among AIs from Six Log Files

On the integrity of the Arabic TTS Arena leaderboard

Beyond the Aggregate Score: Per-Country Domain Shift in the GWHD Wheat Head Detection Model Zoo

Uncensor any LLM with abliteration

Day-0 Muse Glimmer Support on Intel Platforms with vLLM and Hugging Face

Mastering Tensor Dimensions in Transformers

Luth-2: Pushing the French Capabilities of SLMs with MOPD

View all articles