๐ค LLM + โ๏ธ email = ๐ฅ llmail
A bunch of experiments for running local LLM-s to label incoming emails.
conda create -n llmail python=3.11
pip install -r requirements.txt
- Create an app password for your gmail account
cp .env.exammple .env
You can try work in progress notebooks in the experiments
folder.
I am looking to reduce llama 2 CPU latency as much as possible. Let me know if you have a good solution. I am exploring FHE/MPC, Speculative sampling and MoE ATM.