Hardware
In the fight to defend openness in AI, the Marin project is a precious demonstration of openness in model training, with open code, data, re…
In the fight to defend openness in AI, the Marin project is a precious demonstration of openness in model training, with open code, data, recipes, even experimental results. Releasing AI research open
In the fight to defend openness in AI, the Marin project is a precious demonstration of openness in model training, with open code, data, recipes, even experimental results. Releasing AI research openly used to be the norm; I'm grateful for @percyliang's open lab approach. 🚢 Marin 535B-A23B started training this week! As usual, the whole process is open. Voyage plan: pretraining (80%) + midtraining (20%) on 18.75T tokens on 11 x GB200 NVL72 for ~3 months (2.7e24 FLOPs). Post-training will follow. Before kicking off the run, we trained a 4-rung sca…
Related
- Life Cycle Assessment of Pre-training the Lucie 7B Open-Source Large Language Model on the Jean Zay Supercomputer
- Releasing vui an open source voice mode 300M TTS model Runs on a single consumer gpu / apple sillicon Context aware speech 6 minutes of cont…
- Run DiffusionGemma on NVIDIA for Developer-Ready, High-Throughput Text Generation
Source: Andrew Ng (X) | 2026-08-24