pull down to refresh

Gemma 3n models: designed for efficient execution on everyday devicesollama.com/library/gemma3n
124 sats \ 5 comments \ @m0wer 6 Jul AI
write
preview
related posts
0 sats \ 4 replies \ @optimism 6 Jul
Since this doesn't support tools, I thought I'd give it a text instruction.
>>> draw a picture of a question mark

     _,-._
    / \_/ \
   >-(_)-<
    \_/ \_/
      `-'

Here's a simple text-based drawing of a question mark! 😊 

Let me know if you'd like a different style! 🎨
I must be getting old, lol. If there is an artsy stacker that can explain to me how this is a question mark, I'd appreciate it!
reply
101 sats \ 3 replies \ @m0wer OP 6 Jul
Large Language Models are not suited for ASCII art. They tokenize the input and only generate tokens as output. They lose a lot of spatial information and are not really trained for aligning the characters of the output.
It's similar to painting with a hammer. A very skilled person might do something that resembles art, but a hammer is not really meant for that😂
reply
29 sats \ 2 replies \ @optimism 6 Jul
Gotta push the limits. Also the readme says its multimodal, so I was expecting a jpg lol.
reply
100 sats \ 1 reply \ @m0wer OP 6 Jul
It's multimodal for input, not output unfortunately.
reply
0 sats \ 0 replies \ @optimism 6 Jul
I wonder how much can be improved by removing 139 languages, and audio and video modality.
reply