Help with llama-2-7b-chat.Q4_K_M.gguf already in local downloads

#23
by RaphaellG - opened

So I have a slow internet connection and so my localgpt project is failing to download this model, but instead i downloaded it outside of the project with Internet Download Manager but now i dont know how or where to move that file so that it can be in the project and next time that i try to run the localgpt project it will recognize the llama-2-7b-chat.Q4_K_M.gguf as already downloaded. please help
Screenshot (52).png
Screenshot (53).png

@RaphaellG you should just get the path of the file.
I dont exactly know how localgpt works, but wherever you put what model you want, i think putting the path there might work?
Thats usually how huggingface transformers and llama cpp works.

Sign up or log in to comment