update system prompt

fix max_token > n_ctr(512 for llama_cpp) issue

add shutil

try to fix del

try to fix del function

add del button

update ignore

fixed file name

try multi-session

make persona shorter

update persona

update persona

fixed indentation

change transformers parameter to llama_cpp parameters

fix llama import

try gguf.py

fixed model name

Clean initial commit without large files