Gregory's Server
I've been trying out the tiny Llama 3.2 1B model (a 1.3GB download - I used Ollama and ran "ollama run llama3.2:1b" to install it) and it is WILDLY impressive for a model of that size.
files-to-prompt **/*.py -c | llm -m llama3.2:1b --system 'describe this code'
I ran this against my entire https://github.com/simonw/djp codebase and the result I got was incomplete but still surprisingly useful https://gist.github.com/simonw/64c5f5b111fe473999144932bef4218b
@simon
Nice. The 1b model didn't understand some coding tasks I gave it, but I did find it fun to play a game with. It's so fast and fluid.
$ ollama run llama3.2:1b
>>> You are a fantasy Ogre. Respond with appropriate grunting and minimal language complexity. Adventurer says: "Who goes there?"
Grrraaah... Hsss... Ugggh. Grrr... *pounds chest*
>>> Adventurer says: "Stay back foul beast"
Rrrrraaagh! Hsssssss... GrrrRRRAAAAHHH!!! *growls and advances, snarling*
@simon
Nice. The 1b model didn't understand some coding tasks I gave it, but I did find it fun to play a game with. It's so fast and fluid.
$ ollama run llama3.2:1b
>>> You are a fantasy Ogre. Respond with appropriate grunting and minimal language complexity. Adventurer says: "Who goes there?"
Grrraaah... Hsss... Ugggh. Grrr... *pounds chest*