view article Article The 1 Billion Token Challenge: Finding the Perfect Pre-training Mix Nov 3, 2025 β’ 58
Running Featured 1.3k FineWeb: decanting the web for the finest text data at scale π· 1.3k Generate a curated webβtext dataset for LLM training
Running 3.7k The Ultra-Scale Playbook π 3.7k The ultimate guide to training LLM on large GPU Clusters
The Instruction Gap: LLMs get lost in Following Instruction Paper β’ 2601.03269 β’ Published Dec 19, 2025 β’ 8
Running on CPU Upgrade Featured 3k The Smol Training Playbook π 3k The secrets to building world-class LLMs
view reply You don't really have to clone the repo. The FastAPI code is just there for demonstration, and you can code the way you like. The main takeaway is the Dockerfile.
view article Article How to generate text: using different decoding methods for language generation with Transformers Mar 1, 2020 β’ 288
Komodo: A Linguistic Expedition into Indonesia's Regional Languages Paper β’ 2403.09362 β’ Published Mar 14, 2024 β’ 11