Hugging Face

Building Pakistan Notice Helper: A Small AI Tool for a Very Local Safety Problem

Back to Articles Building Pakistan Notice Helper: A Small AI Tool for a Very Local Safety Problem Team Article Published June 8, 2026 Upvote 1 Abid Ali Awan kingabzpro build-small-hackathon For the Hugging Face Build Small Hackathon , I wanted to build something practical,…

The Open Source Community is backing OpenEnv for Agentic RL

Back to Articles The Open Source Community is backing OpenEnv for Agentic RL Published June 8, 2026 Update on GitHub Upvote 1 ben burtenshaw burtenshaw Joseph Spisak spisakjo Lysandre lysandre Davide Testuggine darktex will brown willcb Charles Frye charlesfrye Chris Wing…

Amazing Digital Dentures (a failed project)

Back to Articles Amazing Digital Dentures (a failed project) Team Article Published June 7, 2026 Upvote 1 Virus Dumb VirusDumb build-small-hackathon So my idea was simple and a bit complicated at the same time, Have you guys watched The Amazing Digital Circus? it's an animated…

Sponsors especially OPENAI CODEX voucher usage for codex - openAI challange

Back to Articles Sponsors especially OPENAI CODEX voucher usage for codex - openAI challange Team Article Published June 7, 2026 Upvote 1 specimba specimba build-small-hackathon yuvraj sharma ysharma build-small-hackathon AK akhaliq build-small-hackathon hysts hysts…

Her · हेर — a detective for your Claude Code sessions

Back to Articles Her · हेर — a detective for your Claude Code sessions Team Article Published June 7, 2026 Upvote - Ashish Chalke geekwrestler build-small-hackathon Her · हेर — Marathi for “detective.” A detective for your Claude Code sessions. Try it here: Her on Hugging Face…

Five labs, five minds: building a multi-model finance drama on small models

Back to Articles Five labs, five minds: building a multi-model finance drama on small models Team Article Published June 6, 2026 Upvote - Lester Leong AdmiralTaco build-small-hackathon A second Build Small Hackathon field report: what happens when each agent in an emergent…

Job Searcher

Back to Articles Job Searcher Team Article Published June 6, 2026 Upvote 2 Emre emrekuruu build-small-hackathon Job hunting as a new grad is a full-time job by itself. You sift through hundreds of postings every week to find a handful worth applying to. You click "Easy Apply"…

Persona Atlas: Mapping How Famous Minds Think

Back to Articles Persona Atlas: Mapping How Famous Minds Think Team Article Published June 6, 2026 Upvote - insuperabilehart insuperabile build-small-hackathon TL;DR. Persona Atlas turns a public figure into a behavioral portrait you can actually measure. You type a name, a…

Thousand Token Wood: shipping a multi-agent economy on a 3B model

Back to Articles Thousand Token Wood: shipping a multi-agent economy on a 3B model Team Article Published June 5, 2026 Upvote - Lester Leong AdmiralTaco build-small-hackathon A Build Small Hackathon field report on what a 3-billion-parameter council of traders can and cannot do.…

Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI

Back to Articles Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI Enterprise + Article Published June 4, 2026 Upvote - Varun Singh varunsingh nvidia Isabel Hulseman ihulseman0220 nvidia Anuj Doshi andoshi nvidia Shyamala Prayaga sprayaga25…

How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent

Back to Articles How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent Enterprise + Article Published June 4, 2026 Upvote - Maryam Motamedi maryameee nvidia Adi- margolin Amargolin nvidia Francesco fciannella nvidia Myungjong Kim Myungjong nvidia Enas Albasiri…

EVA-Bench Data 2.0: 3 Domains, 121 Tools, 213 Scenarios

Back to Articles EVA-Bench Data 2.0: 3 Domains, 121 Tools, 213 Scenarios Enterprise Article Published June 4, 2026 Upvote 2 Tara Bogavelli tarabogavelli ServiceNow-AI Gabrielle Gauthier Melancon gabegma ServiceNow-AI Katrina Stankiewicz kstankiewicz ServiceNow-AI Nifemi Bamgbose…

Task-Seeded Synthetic Q&A Generation for Nemotron Pretraining

Back to Articles Task-Seeded Synthetic Q&A Generation for Nemotron Pretraining Enterprise + Article Published June 4, 2026 Upvote - Markus Kliegl mkliegl-nv nvidia Dan Su sudandandansu1 nvidia Author: Dan Su In large-scale LLM development, the question is no longer simply how…

Designing the hf CLI as an agent-optimized way to work with the Hub

Back to Articles Designing the hf CLI as an agent-optimized way to work with the Hub Published June 4, 2026 Update on GitHub Upvote 4 Célina Hanouti celinah Lucain Pouget Wauplin hf is the official command-line entrypoint to the Hugging Face Hub. Anything you can do on the Hub…

Direct Preference Optimization Beyond Chatbots

Back to Articles Direct Preference Optimization Beyond Chatbots Team Article Published June 3, 2026 Upvote - Erick Lachmann ErickvL Dharma-AI Pimenta de Freitas Cardoso GabrielPimenta99 Dharma-AI Using Rejection Pairs From Your Model's Own Failures In April, we released…

Adding MCP Tools to Reachy Mini

Back to Articles Adding MCP Tools to Reachy Mini Published June 3, 2026 Update on GitHub Upvote - Alina Lozovskaya alozowski Reachy Mini no longer has to look out the window to tell you the weather The Reachy Mini conversation app can now use tools hosted in public Hugging Face…

Holo3.1: Fast & Local Computer Use Agents

Back to Articles Holo3.1: Fast & Local Computer Use Agents Team Article Published June 2, 2026 Upvote 13 Maxime Langevin maxime-hcompany Hcompany Hamza Benchekroun hamza-hcompany Hcompany Axel Moyal axmoy Hcompany Emrick Sinitambirivoutin emricksini-h Hcompany Antonio Loison…

Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains

Back to Articles Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains Team Article Published June 1, 2026 Upvote 5 Nikita Pavlichenko pavlichenko JetBrains Mellum2 is a 12B-parameter Mixture-of-Experts model trained from scratch on natural language and code. The…

Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic

Back to Articles Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic Enterprise Article Published June 1, 2026 Upvote - Fuller nfuller ibm-research Guides have aided humanity throughout history. Prehistoric civilizations understood that the sun and the moon…

Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action

Back to Articles Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action Enterprise + Article Published June 1, 2026 Upvote - Asawaree asawareeb nvidia Atharva Joshi atharvajoshi10 nvidia NVIDIA Cosmos 3 is here - and it's available on Hugging…

Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler

Back to Articles Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler Published May 29, 2026 Update on GitHub Upvote 7 Aritra Roy Gosthipaty ariG23498 Sayak Paul sayakpaul Sergio Paniego sergiopaniego Rémi Ouazan Reboul ror Pedro Cuenca pcuenq What you cannot…

ITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM

Back to Articles ITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM Enterprise Article Published May 27, 2026 Upvote 3 Ayhan Sebin ayhansebin ibm-research Saurabh Jha saurabhjha1 ibm-research Rohan…

Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL

Back to Articles Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL Published May 27, 2026 Update on GitHub Upvote 1 Amine Dirhoussi aminediroHF Quentin Gallouédec qgallouedec Kashif Rasul kashif Lewis Tunstall lewtun Edward Beeching edbeeching Albert…

Reachy Mini goes fully local

Back to Articles Reachy Mini goes fully local Published May 27, 2026 Update on GitHub Upvote 8 Amir Mahla A-Mahla Andres Marafioti andito After building your Reachy Mini, you'll install the conversation app and start talking to it. Until now, you had to send your audio to a…

Harness, Scaffold, and the AI Agent Terms Worth Getting Right

Back to Articles Harness, Scaffold, and the AI Agent Terms Worth Getting Right Published May 25, 2026 Update on GitHub Upvote - Sergio Paniego sergiopaniego Aritra Roy Gosthipaty ariG23498 When a field evolves quickly, its vocabulary often evolves faster than its shared…

Towards Speed-of-Light Text Generation with Nemotron-Labs Diffusion Language Models

Back to Articles Towards Speed-of-Light Text Generation with Nemotron-Labs Diffusion Language Models Enterprise + Article Published May 23, 2026 Upvote - Mehran Maghoumi MMaghoumi nvidia Yonggan Fu YongganFu nvidia Pavlo Molchanov pmolchanov nvidia Khadkevich mkhadkevich nvidia…

Specialization Beats Scale: A Strategic Variable Most AI Procurement Decisions Overlook

Back to Articles Specialization Beats Scale: A Strategic Variable Most AI Procurement Decisions Overlook Team Article Published May 22, 2026 Upvote - Erick Lachmann ErickvL Dharma-AI Pimenta de Freitas Cardoso GabrielPimenta99 Dharma-AI When a model’s training history is moved…

OlmoEarth v1.1: A more efficient family of models

Back to Articles OlmoEarth v1.1: A more efficient family of models Team Article Published May 19, 2026 Upvote 1 Kyle Wiggers Ai2Comms allenai 🧠 Models: https://huggingface.co/collections/allenai/olmoearth | 📄 Tech Report: https://allenai.org/papers/olmoearth_v1_1 | 💻 Code:…

Introducing the Ettin Reranker Family

Back to Articles Introducing the Ettin Reranker Family Published May 19, 2026 Update on GitHub Upvote 6 Tom Aarsen tomaarsen TL;DR Today I'm releasing six new Sentence Transformers CrossEncoder rerankers, state-of-the-art at their respective sizes, built on top of the Ettin…

Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation

Back to Articles Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation Enterprise + Article Published May 18, 2026 Upvote - Ting-Yun Chang ting-yunc nvidia Miguel Martin miguelmartin-nv nvidia Jonathan Allen nv-spectralflight nvidia Ke Ding kding1…

PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend

Back to Articles PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend Team Article Published May 18, 2026 Upvote 12 AlexZhang AlexTransformer PaddlePaddle cuicheng ChengCui PaddlePaddle Jun Zhang jzhang533 PaddlePaddle Manhui Lin gggdddfff…

The Open Agent Leaderboard

Back to Articles The Open Agent Leaderboard Enterprise Article Published May 18, 2026 Upvote 1 Elron Bandel Elron ibm-research How good are general purpose AI agents? We built an open evaluation framework to find out. Most evaluations in AI report a simple result: what score…

Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality

Back to Articles Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality Enterprise Article Published May 14, 2026 Upvote - Radu Florian hansolosan ibm-granite Parul Awasthy pawasthy ibm-granite Aashka Trivedi…

Unlocking asynchronicity in continuous batching

Back to Articles Unlocking asynchronicity in continuous batching Published May 14, 2026 Update on GitHub Upvote 6 Rémi Ouazan Reboul ror Pedro Cuenca pcuenq Aritra Roy Gosthipaty ariG23498 TL;DR: we explain how to separate CPU and GPU workloads to get a massive performance boost…

Cursor 0.50 ships — agent mode + multi-file edits

The Cursor IDE team rolled out 0.50 with a redesigned agent panel, multi-file refactor flow, and native support for Anthropic + OpenAI tool-use APIs.

Building Blocks for Foundation Model Training and Inference on AWS

EMO: Pretraining mixture of experts for emergent modularity

vLLM V0 to V1: Correctness Before Corrections in RL

Adding Benchmaxxer Repellant to the Open ASR Leaderboard

Granite 4.1 LLMs: How They’re Built

DeepInfra on Hugging Face Inference Providers 🔥

Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents

How to build scalable web apps with OpenAI's Privacy Filter

DeepSeek-V4: a million-token context that agents can actually use

How to Use Transformers.js in a Chrome Extension

QIMMA قِمّة ⛰: A Quality-First Arabic LLM Leaderboard

AI and the Future of Cybersecurity: Why Openness Matters

Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational Agents

The PR you would have opened yourself

Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers