llama.cpp: update submodule for "code" model crash workaround #2382
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
# for free
to join this conversation on GitHub.
Already have an account?
# 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Outdated suggestions cannot be applied.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.
This PR pulls in nomic-ai/llama.cpp@f67f465, which is a workaround for ggerganov/llama.cpp#7592 so that some models with "code" in their name won't crash at load time.
Without this change, this model crashes GPT4All if you try to load it (not 100% reliably since this is caused by UB - with
-DCMAKE_BUILD_TYPE=Debugon Linux it will always crash if you have libstdc++). With this change, it loads successfully.Fixes #2379