llm
llm copied to clipboard
simonw
Access large language models from the command-line
I rebuilt my docker image this morning, and after I did so my application broke. Here’s a reproduction: ```shell ➜ /tmp rm -Rf .venv ➜ /tmp python3 -m venv .venv...
Please add NVIDIA Cloud API: https://docs.api.nvidia.com/nim/reference/meta-llama3-70b-infer Should be very similar to llm-perplexity (https://github.com/hex/llm-perplexity)
Frequently, I was wondering what was wrong when I just typed `llm` and it sat at an empty terminal, without any error but without doing anything. IMO it would be...
I noticed a few people were raising issues about "exceeding quota" so I added a "Note:" to this doc so people know where to go to add credit to their...
would be interesting to add markdown output preview built in. for now i'm using it with `glow` https://github.com/charmbracelet/glow to do the same 
### Background / context - was originally following install instructions for Mac at https://simonwillison.net/2023/Aug/1/llama-2-mac/ - yeah, I should have spotted that this was an older post....but I didn't - Macbook...
while there's the docs page, beyond that it's really the wild west out here - today I searched github for "llm install -e '.[test]'". Lots of other unrelated projects come...
# Overview Fixes #12 This builds on the excellent foundation that @juftin laid down in #278 and 1. fixes a mysterious bug that was failing some tests and 2. resolves...
