Skip to content

Running convert-pth-ggml.py on Linux #852

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
linuxmagic-mp opened this issue Apr 8, 2023 · 3 comments
Closed

Running convert-pth-ggml.py on Linux #852

linuxmagic-mp opened this issue Apr 8, 2023 · 3 comments

Comments

@linuxmagic-mp
Copy link

A not so obvious error, Using Hugging Face llama-13b-hf as the model, I get a 'no such file' for params.json
(Following README, but don't have a params.json. Are we supposed to build one? Might want to update README for this situation.

python3.10 convert-pth-to-ggml.py ../llama-13b-hf/ 1

@Technetium1
Copy link

You didn't make the same directory structure for models as it asked, might be important to run in that folder.

@linuxmagic-mp
Copy link
Author

Yeah, that doesn't make a difference, it looks in the ./models/13B for the file, but the params.json doesn't exist in the llama-13b-hf repo

@prusnak
Copy link
Collaborator

prusnak commented Apr 8, 2023

You need to download the params.json (in another word, download the weights from repository that have the file, not from the ones that haven't).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants