You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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?
Activity
cs-mt commentedon Mar 13, 2023
Oh, never mind. Allocating extra swap space worked.
kassane commentedon Mar 15, 2023
@cs-mt ,
I got the same error having 16GiB RAM. Probably 32GiB would be ideal.
Ref: #138
Merge pull request ggml-org#76 from anzz1/patch-3
docs: experiment #76 — temperature grid search confirms defaults optimal
merge: experiment #76 — temperature grid search confirms αV=1.3 optimal
iq4_nl: faster quantization (ggml-org#76)
fix: resolve code scanning alerts ggml-org#76-#100