Running on CPU Upgrade Featured 3.34k The Smol Training Playbook π 3.34k The secrets to building world-class LLMs
google/embeddinggemma-300m Sentence Similarity β’ 0.3B β’ Updated Sep 25, 2025 β’ 2.36M β’ β’ 2.06k
Running on Zero Agents Featured 1.79k Dia 1.6B π― 1.79k Generate realistic dialogue from a script, using Dia!
Running 4.1k The Ultra-Scale Playbook π 4.1k The ultimate guide to training LLM on large GPU Clusters
Running 96 Scaling FineWeb to 1000+ languages: Step 1: finding signal in 100s of evaluation tasks π 96 Evaluate multilingual models using FineTasks
Running 139 TxT360: Trillion Extracted Text π 139 Explore and download the TxT360 LLM preβtraining dataset