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.

Sign up for GitHub

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

Jump to bottom

.pth to .ggml Out of Memory #76

Closed
cs-mt opened this issue Mar 13, 2023 · 2 comments
Closed

.pth to .ggml Out of Memory #76

cs-mt opened this issue Mar 13, 2023 · 2 comments
Labels
hardware Hardware related wontfix This will not be worked on

Comments

@cs-mt
Copy link

cs-mt commented Mar 13, 2023

I have 16 GBs of memory (14 GB free) and running python3 convert-pth-to-ggml.py models/7B/ 1 causes an OOM error (Killed) on Linux.

Here's the dmesg message:
Out of memory: Killed process 930269 (python3) total-vm:15643332kB, anon-rss:13201980kB, file-rss:4kB, shmem-rss:0kB, UID:0 pgtables:26524kB oom_score_adj:0

I will be receiving my new RAM in a few days but I think this is supposed to work with 16 GB memory?
@cs-mt
Copy link
Author

cs-mt commented Mar 13, 2023

Oh, never mind. Allocating extra swap space worked.

@cs-mt cs-mt closed this as completed Mar 13, 2023
@kassane
Copy link
Contributor

kassane commented Mar 15, 2023 •
edited
Loading

@cs-mt ,
I got the same error having 16GiB RAM. Probably 32GiB would be ideal.

Ref: #138

@gjmulder gjmulder added wontfix This will not be worked on hardware Hardware related labels Mar 15, 2023
Hades32 pushed a commit to Hades32/llama.cpp that referenced this issue Mar 21, 2023
@antimatter15
Merge pull request ggml-org#76 from anzz1/patch-3
2cbe796 
add cached torrent links
@Bearsaerker Bearsaerker mentioned this issue Mar 12, 2025
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
hardware Hardware related wontfix This will not be worked on
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@kassane @gjmulder @cs-mt