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 a 6GB Graphics card and I am using:
EMBEDDING_MODEL_NAME = "hkunlp/instructor-large"
MODEL_ID = "TheBloke/orca_mini_3B-GGML"
MODEL_BASENAME = "orca-mini-3b.ggmlv3.q4_0.bin"
When I run run_localGPT.py
what is senate -> OK
what is congress -> OK
what is president -> OK
how many senators are in the senate -> OK
what is the power of the senate -> Segmentation fault (sometimes)
what is the power of the congress -> Segmentation fault (sometimes)
How can I stop segmentation faults?
(P.S. If I give some breaks between questions, I get less segmentation faults.)
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
I have a 6GB Graphics card and I am using:
EMBEDDING_MODEL_NAME = "hkunlp/instructor-large"
MODEL_ID = "TheBloke/orca_mini_3B-GGML"
MODEL_BASENAME = "orca-mini-3b.ggmlv3.q4_0.bin"
When I run run_localGPT.py
How can I stop segmentation faults?
(P.S. If I give some breaks between questions, I get less segmentation faults.)
Beta Was this translation helpful? Give feedback.
All reactions