Back
Similar todos
Run openllm dollyv2 on local linux server
installed cody to cursor, so that i can use llama3.1 and gemma2 via ollama 
#astronote 
#leifinlavida
switch 
#therapistai to Llama 3.1
test #therapistai with Llama 3-70B
implemented ollama local models 
#rabbitholes
check out Llama 3.1 
#life
plugin comparison 
#ekh
test OpenHermes 2.5 Mistral LLM
🤖 Tried out Llama 3.3 and the latest Ollama client for what feels like flawless local tool calling. 
#research
switch #therapistai fully to Llama3-70B
Ran some local LLM tests 🤖
published a test package
testing hookmonitor 
#integratewp
🤖 spent some time getting Ollama and langchain to work together. I hooked up tooling/function calling and noticed that I was only getting a match on the first function call. Kind of neat but kid of a pain.
read llama guard paper 
#aiplay
add pre-commit git hook testing lambda code