Remove duplicate BOS token from LlamaCppInterface prompt formatting - #2
Open
tobybaratta wants to merge 1 commit into
Open
Remove duplicate BOS token from LlamaCppInterface prompt formatting#2tobybaratta wants to merge 1 commit into
tobybaratta wants to merge 1 commit into
Conversation
error message I got: ``` Loaded 30 participant responses. Starting theme extraction for 30 documents... Step 1: Extracting themes from documents... Processing document 1/30... E:\compassion-themecloud\.venv\Lib\site-packages\llama_cpp\llama.py:1314: RuntimeWarning: Detected duplicate leading "<|begin_of_text|>" in prompt, this will likely reduce response quality, consider removing it... warnings.warn( ``` ran using Meta-Llama-3.1-8B-Instruct GGUF + llama-cpp-python 0.3.35.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description:
llama-cpp-python automatically adds the BOS token for GGUF models that specify it in model metadata. LlamaCppInterface currently manually prepends <|begin_of_text|>, causing llama-cpp-python to emit a duplicate-BOS warning:
Log:
Ran using Meta-Llama-3.1-8B-Instruct GGUF + llama-cpp-python 0.3.35. On Windows. :/
(Sorry for PR from default fork, was a wee bit too hasty.)
thank you for making such an awesome tool!!