view reply All the experiments are run on A100s, so I don't think it uses the optimized flash attention, right?
view article Article The GPT-OSS models are here… and they’re energy-efficient! By sasha • 13 days ago • 19
view article Article Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face By abidlabs and 4 others • 23 days ago • 156
view article Article Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face By abidlabs and 4 others • 23 days ago • 156
view article Article SmolLM3: smol, multilingual, long-context reasoner By loubnabnl and 22 others • Jul 8 • 631
view article Article How Much Power does a SOTA Open Video Model Use? ⚡🎥 By jdelavande and 2 others • Jul 2 • 14
view article Article Saying Thank You to a LLM Isn't Free — Measuring the Energy Cost of Politeness By jdelavande and 2 others • Jun 12 • 21
Running 57 57 StableDiffusionBiasExplorer 📊 Browse gender-biased images generated by models based on prompts