[HN Gopher] PaliGemma
       ___________________________________________________________________
        
       PaliGemma
        
       Author : tosh
       Score  : 76 points
       Date   : 2024-05-14 18:30 UTC (4 hours ago)
        
 (HTM) web link (ai.google.dev)
 (TXT) w3m dump (ai.google.dev)
        
       | tosh wrote:
       | How does this model compare to the 3b Gemma if I would use it
       | only with text?
        
         | coder543 wrote:
         | Well, to start with, there is no regular 3B Gemma. There are 2B
         | and 7B Gemma models. I would guess this model is adding an
         | extra 1B parameters to the 2B model to handle visual
         | understanding.
         | 
         | The 2B model is not very smart to begin with, so... I would
         | expect this one to not be very smart either if you only use it
         | for text, but I wouldn't expect it to be _much_ worse. It could
         | potentially be useful /interesting for simple visual
         | understanding prompts.
        
       | mmastrac wrote:
       | This is an impressive amount of public AI work coming out of
       | Google. The competition we're seeing here is really pushing
       | things forward.
        
       | curl-up wrote:
       | Anyone here have experience with extracting image embeddings out
       | of these models? All the image emb. models I tried so far were
       | quite bad for my use cases, and I feel that hidden
       | representations of models like these might be much better.
        
       | m3kw9 wrote:
       | Google markets their new tech like arxiv articles. They have lots
       | to learn from OpenAI
        
       ___________________________________________________________________
       (page generated 2024-05-14 23:00 UTC)