tree-of-thought-llm

tree-of-thought-llm copied to clipboard

In order to run the experiment, first, I write a run script called jiaoben.py: import argparse from tot.methods.bfs import solve from tot.tasks.game24 import Game24Task args = argparse.Namespace(backend='gpt-3.5', temperature=0.1, task='game24', naive_run=False,...

wuyingxu

Code for GSM8K and StrategyQA

1

Hey, First off, thanks a lot for your work, I really appreciated going through both your paper and the code. In the appendix of your paper you reported some results...

Potamitisn

I am running into this error with python 3.10 or 3.12 after "pip3 install -U tree-of-thoughts" . Any thoughts? ``` Traceback (most recent call last): File "", line 1, in...

qingerVT

I'm a little confused about how majority voting evaluation work. Does that mean that we prompt the LLM n times, each time choosing a best candidate and count the votes?...

xinyilizard

Thanks for your great work! I have a few questions: 1.How do you design best of k settings in IO and CoT? Does it use a reward model? 2.What is...

icezqz