switch #therapistai to Llama 3.1

Check out llama life #life

download Llama3-70B and Llama3-8B #life

✏️ wrote about running Llama 3.1 locally through Ollama on my Mac Studio. micro.webology.dev/2024/07/24…

try client side web based Llama 3 in JS #life webllm.mlc.ai/

install finally ollama with llama3 #life

try llama_index #autorepurposeai

ollama is worth using if you have an M1/M2 mac and want a speedy way to access the various llama2 models.

test #therapistai with Llama 3-70B

Explore llama 3 8b for embeddings

switch #therapistai fully to Llama3-70B

#thecompaniesapi run my phi3-128k flow using llama3.1 and the results are mind blowing, it's insane how good llama is at conserving context and original purpose even when supplied with thousands of tokens; also shipped multiple hotfixes in robot UI; about to merge a month of work and then hop on fine tuning

got llama3 on groq working with cursor 🤯

🤖 more working with Ollama and Llama 3.1 and working on a story writer as a good enough demo. #research

deploy Llama3-70B on #therapistai for me

trying to stream response from llama #autorepurposeai

test Vision model coop with Llama3 #therapistai

🤖 played with Aider and it mostly working with Ollama + Llama 3.1 #research

more fun with LLAMA2 and figuring out how to better control/predict stable output

Playing with llama2 locally and running it from the first time on my machine