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

check out Llama 3.1 #life

#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

wrote a guide on llama 3.2 #getdeploying

🤖 Tried out Llama 3.3 and the latest Ollama client for what feels like flawless local tool calling. #research

🤖 Updated some scripts to use Ollama's latest structured output with Llama 3.3 (latest) and fell back to Llama 3.2. I drop from >1 minute with 3.3 down to 2 to 7 seconds per request with 3.2. I can't see a difference in the results. For small projects 3.2 is the better path. #research

got distracted with my writer AIs — testing between llama3.1 vs gemma2 #leifinlavida

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

test #therapistai with Llama 3-70B

🧑‍🔬 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…

switch #therapistai to Llama 3.1

#thecompaniesapi lots of fixes on the queue ; trying to get the llm stable ; refactor of sources

Ran some local LLM tests 🤖

🤖 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

Test automating some translations with Llama.

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

🤖 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

#thecompaniesapi port back my ai wrapper improvements on our existing llama stack and prepare fine tuning for phi3

#thecompaniesapi port back my ai wrapper improvements on our existing llama stack and prepare fine tuning for phi3