A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/
Thorough improvement of evaluation function. Is now working much simpler instead of complex regex functions.
Updated the thoughtsource_100 datasets evaluations in json.
Made function for loading the thoughtsource_100 collection.
Thorough improvement of evaluation function. Is now working much simpler instead of complex regex functions. Updated the thoughtsource_100 datasets evaluations in json. Made function for loading the thoughtsource_100 collection.