Add thinking prefix and tool response for empty assistant messages#13
Draft
AlexCuadron wants to merge 112 commits intomainfrom
Draft
Add thinking prefix and tool response for empty assistant messages#13AlexCuadron wants to merge 112 commits intomainfrom
AlexCuadron wants to merge 112 commits intomainfrom
Conversation
- Added update_llm_config_for_completions_logging to imports
- Modified get_config to accept instance parameter
- Updated llm_config to enable completions logging
- Updated process_instance to pass instance to get_config
This change makes aider_bench save llm_completions in the same way as swe_bench,
with completions being saved in {eval_output_dir}/llm_completions/{instance_id}/
…tions-fork feat: Enable llm_completions logging in aider_bench
…execute_bash, finish, str_replace_editor)
…polyglot_benchmark
…path matching and debugging output
Add polyglot benchmark implementation
- Added update_llm_config_for_completions_logging to imports
- Modified get_config to accept instance parameter
- Updated llm_config to enable completions logging
- Updated process_instance to pass instance to get_config
This change makes aider_bench save llm_completions in the same way as swe_bench,
with completions being saved in {eval_output_dir}/llm_completions/{instance_id}/
… solution parameter
…n AIME2024 benchmark
…0 and AIME2024 benchmarks
Merge AIME2024 benchmark into main
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 adds a feature to the LLM class that automatically adds a thinking prefix and tool response when the first assistant message is empty. This makes the model believe that certain Python libraries (sympy, numpy, scipy, matplotlib) are already installed and available for use.
Changes
llm.pyto check for empty assistant messages and insert the thinking prefix and tool responseREADME_thinking_prefix.mdTesting
The changes have been tested with a mock LLM completion function to verify that the thinking prefix and tool response are correctly added.