Fail hard if model can't be loaded. #504
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
I have the same problem, is there any solution? |
In my case the problem was related to old CPU not compatible with AVX2 instructions. Compiling llama-cpp-python with AVX2 off fixed the problem. |
|
The PR looks similar to #491 |
|
@matinlotfali yup, it is. I'm not sure how much sense it make to continue (return None) if model load fails. In this PR I changed it to just fail hard (and not try to continue) to prevent "cryptic" messages later (caused by no model present). #491 adds warning, but continues. |
|
We need a combination of both PRs |
|
Hi @matinlotfali , I have updated this PR, combining both things. Please review. Thanks! |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
when model fail to load, it returns None, which later results into
I had hard time to find out what's the problem (in my case it was missing AVX2 CPU support). Revealing the original load error message would be much easier to follow and debug.