Running 39 Korean Open Source Heatmap π₯ 39 Explore Korean AI open source contributions and releases
Running 89 Scaling FineWeb to 1000+ languages: Step 1: finding signal in 100s of evaluation tasks π 89 Evaluate multilingual models using FineTasks
Running 79 Maintain the unmaintainable π 79 Explore the complex relationships between 400+ machine learning models
view post Post 1765 We have a new heatmap live on huggingface nowπ₯ woojun-jung/open-source-release-heatmap-koKorean community built their own version to track labs that actively publish open work, inspired by Chinese open source heat map! This is the open source community at its best β₯οΈ See translation 1 reply Β· β€οΈ 3 3 + Reply
Running 39 Korean Open Source Heatmap π₯ 39 Explore Korean AI open source contributions and releases
Running 109 The Eiffel Tower Llama π 109 Explore the Eiffel Tower Llama experiment with open-source models
Visual Funnel: Resolving Contextual Blindness in Multimodal Large Language Models Paper β’ 2512.10362 β’ Published Dec 11, 2025 β’ 1
Running Featured 1.31k FineWeb: decanting the web for the finest text data at scale π· 1.31k Generate a curated webβtext dataset for LLM training
Running 3.74k The Ultra-Scale Playbook π 3.74k The ultimate guide to training LLM on large GPU Clusters
Running on CPU Upgrade Featured 3.04k The Smol Training Playbook π 3.04k The secrets to building world-class LLMs