Comment on Google Reveals Gemini, rival to GPT-4
UFODivebomb@programming.dev 11 months ago
Is this a transformer model? Any details?
Comment on Google Reveals Gemini, rival to GPT-4
UFODivebomb@programming.dev 11 months ago
Is this a transformer model? Any details?
catastrophicblues@lemmy.ca 11 months ago
Here is their technical report. I’m yet to read it, though.
UFODivebomb@programming.dev 11 months ago
Thanks! Here’s the high level description from there:
“Gemini models build on top of Transformer decoders (Vaswani et al., 2017) that are enhanced with improvements in architecture and model optimization to enable stable training at scale and optimized inference on Google’s Tensor Processing Units. They are trained to support 32k context length”