TGViewer
Linkstream Linkstream @linkstream · 169 subscribers
Post #620 263
hey look, you can train GPT-2 in under an hour*
* using about $40M worth of hardware. still impressive, though
https://devblogs.nvidia.com/training-bert-with-gpus/
NVIDIA Technical Blog NVIDIA Clocks World’s Fastest BERT Training Time and Largest Transformer Based Model, Paving Path For Advanced Conversational AI NVIDIA DGX SuperPOD trains BERT-Large in just 47 minutes, and trains GPT-2 8B, the largest Transformer Network Ever with 8.3Bn parameters Conversational AI is an essential building block of human…
Open in Telegram All posts from @linkstream
More from @linkstream
  1. Oct 6, 2026https://fixupx.com/capacitanas/status/2107153559427145785?s=46
  2. Sep 30, 2026i started doing exactly this (models editing its own context) as a natural extension of sa…
  3. Sep 28, 2026cursed font factory https://bastardica.mitpit.com/
  4. Sep 25, 2026um, ahem, AlphaZero for text. Training language models without language. Loosely, natural…
  5. Sep 23, 2026umm ahem if you don't try to rein in new opus(5.5) you get one more qualitative step in ca…
  6. Sep 23, 2026nice https://fixupx.com/eyalsela/status/2102373749110587443?s=46
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →