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/
MIT License
863
stars
69
forks
source link
give evaluation func the option to return None #96
So far evaluation could only output True/False. But in some cases we just want it to leave the answer not evaluated, and therefor it needs to be able to return None.
So far evaluation could only output True/False. But in some cases we just want it to leave the answer not evaluated, and therefor it needs to be able to return None.