fix(llama.cpp): disable infinite context shifting #1704
Merged
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
✅ Deploy Preview for localai canceled.
|
mudler
force-pushed
the
disable_context_shift
branch
from
89a3363
to
66b4af0
Compare
Infinite context loop might as well trigger an infinite loop of context shifting if the model hallucinates and does not stop answering. This has the unpleasant effect that the predicion never terminates, which is the case especially on small models which tends to hallucinate. Workarounds #1333 by removing context-shifting. See also upstream issue: ggerganov/llama.cpp#3969
mudler
force-pushed
the
disable_context_shift
branch
from
66b4af0
to
22f8902
Compare
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Outdated suggestions cannot be applied.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.
Infinite context loop might as well trigger an infinite loop of context shifting if the model hallucinates and does not stop answering. This has the unpleasant effect that the prediction never terminates, which is the case especially on small models which tends to hallucinate. The behavior is observable when the assigned slot exceed the context size, which triggers context shifting, and can be reproduced by specifying a really small context size window.
Workarounds #1333 by removing context-shifting until it is fixed upstream.
See also upstream issue: ggerganov/llama.cpp#3969