search

HumanSignal / RLHF

Collection of links, tutorials and best practices of how to collect the data and build end-to-end RLHF system to finetune Generative AI models
175 stars 36 forks source link

How to fix the following errors? #6

Open missflash opened 1 year ago

missflash commented 1 year ago

The following error occurred while running cell 10 in 6. Tune language model using PPO with our preference model. After adding __init__.py to /content/trlx/examples/summarize_rlhf/reward_model/, I still get the same error. How can I fix it?

     10 import torch
     11 from datasets import load_dataset
---> 12 from reward_model.reward_model import GPTRewardModel
     13 from tqdm import tqdm
     14 from transformers import AutoTokenizer

ModuleNotFoundError: No module named 'reward_model.reward_model'; 'reward_model' is not a package
VimukthiRandika1997 commented 8 months ago

I got the same issue!