Increase Ollama num_predict to fix JSON truncation on long headlines#43
Open
frederickkeune wants to merge 1 commit into
Open
Increase Ollama num_predict to fix JSON truncation on long headlines#43frederickkeune wants to merge 1 commit into
frederickkeune wants to merge 1 commit into
Conversation
Manual scoring of 30 explanations surfaced two rows falling back to the offline placeholder even with Ollama reachable: the 220-token budget was cutting off the model's JSON reply mid-object on unusually long/quote-heavy headlines, so _extract_explanation had nothing parseable. Bumped to 350 to give the reasoning + explanation fields enough room to complete.
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Manual scoring of 30 explanations surfaced two rows falling back to the offline placeholder even with Ollama reachable: the 220-token budget was cutting off the model's JSON reply mid-object on unusually long/quote-heavy headlines, so _extract_explanation had nothing parseable. Bumped to 350 to give the reasoning + explanation fields enough room to complete.