Skip to content
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

unable to convert #24

Open
chaltik opened this issue May 6, 2023 · 0 comments
Open

unable to convert #24

chaltik opened this issue May 6, 2023 · 0 comments

Comments

@chaltik
Copy link

chaltik commented May 6, 2023

Trying to test the simplest example, I cloned the llama 7b repo, created subfolder models/7B and copied the files there. After this trying to follow the instructions, getting sigfault:
`
(ai) karen@HAL-9000:~/anaconda3/envs/ai/lib/python3.10/site-packages/llamacpp$ ls models/7B/

config.json pytorch_model-00002-of-00002.bin special_tokens_map.json
generation_config.json pytorch_model.bin.index.json tokenizer_config.json
pytorch_model-00001-of-00002.bin README.md tokenizer.model

(ai) karen@HAL-9000:~/anaconda3/envs/ai/lib/python3.10/site-packages/llamacpp$ llamacpp-convert ./models/7B/ 1
Illegal instruction (core dumped)
`
perhaps it's just a matter of me not understanding what needs to be done. This is a CPU box with 24GB RAM

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

1 participant