 Llama 3.2 is out, and it's a much more substantial release than the 3.1 to 3.2 version bump might indicate Four new models, including Meta's first two vision models (11B and 90B) and two new text-only small models (1B and 3B) My notes so far: https://simonwillison.net/2024/Sep/25/llama-32/ 4 comments
@simon That's impressive - I struggled to work out what the photo was. Had to zoom right in before I realised they were in water. 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 |
Gregory's Server
You can try out the vision models on https://lmarena.ai/ by navigating to "Direct Chat" and then selecting those models from the dropdown menu