The slides for the #radare2 #ai presentation made by @pancake are now public! Check them out while they are still hot! https://github.com/radareorg/radare2-extras/blob/master/r2ai/local/r2ai.pdf

@radareorg @pancake I tried using llama-2-7b-chat-codeCherryPop.Q5_K_M.gguf instead of llama-2-7b-chat-codeCherryPop.ggmlv3.q4_K_M.gguf, it's roughly 700mb bigger, gives similar results but supposedly more accurate ("large, very low quality loss - recommended"). Got it from here:
https://huggingface.co/TheBloke/llama2-7b-chat-codeCherryPop-qLoRA-GGUF

@modrobert ideally models from hugging face should be automatically downloadable from r2ai like it's done by open-interpreter, but i somewhat broke the code while messing with the code. now that i have a better idea of what to do and how i'll bring that back and shrink the current spaguetti code

@pancake OK, yes, there were some connection errors until I manually entered the full path to the model in main.py. Perhaps a bit off-topic, but do you think it's possible to get that irc #radare (liberchat) <-> telegram bot going again?

@modrobert seems like the link got broken because the bot is not able to join the telegram channel for a reason :? but then i found that libera.chat banned the matrix bridge too https://matrix.org/blog/2023/08/libera-bridge-disabled/ so i guess i'll need to join the irc again and stay around.. or maybe i can bridge the irc with the fediverse

@pancake OK, thanks for checking.