Back
Similar todos
worked on llama2 experiments mostly to see how easy it is to break it and how good the overall quality is.
more AI story writing. Also, getting a better handle on what various versions of Llama2 can handle.
check out Llama 3.1 
#life
Playing with llama2 locally and running it from the first time on my machine
switch 
#therapistai to Llama 3.1
🤖 lots of AI research last night including writing a functional story bot to wrap my head around how to apply step-by-step logic and get something meaningful out of llama2 
#research
realize #therapistai with Llama3-70B actually understands WTF is going on now
switch #therapistai fully to Llama3-70B
🧑🔬 researching when Llama 2 is as good or better than GPT-4 and when it's not as good. Good read here www.anyscale.com/blog/llama-2…
focus on smoother, more fun lerping 
#mused
✏️ wrote about running Llama 3.1 locally through Ollama on my Mac Studio. micro.webology.dev/2024/07/24…
prototype a simple autocomplete using local llama2 via Ollama 
#aiplay
🤖 played with Aider and it mostly working with Ollama + Llama 3.1 #research
🤖 more working with Ollama and Llama 3.1 and working on a story writer as a good enough demo. #research
trying to stream response from llama 
#autorepurposeai
try client side web based Llama 3 in JS 
#life webllm.mlc.ai/
got distracted with my writer AIs — testing between llama3.1 vs gemma2 
#leifinlavida
ollama is worth using if you have an M1/M2 mac and want a speedy way to access the various llama2 models.