Oasst1 Pairwise Rlhf Reward

Hugging Face

Dataset Card for "oasst1_pairwise_rlhf_reward" OASST1 dataset preprocessed for reward modeling: import pandas as pd from datasets import load_dataset,concatenate_datasets, Dataset, DatasetDict import numpy as np dataset = load_dataset("OpenAssistant/oasst1") df=concatenate_datasets(list(dataset.values())).to_pandas() m2t=df.set_index("message_id")['text'].to_dict() m2r=df.set_index("message_id")['role'].to_dict() m2p=df.set_index('message_id')['parent_id'].to_dict()… See the full description on the dataset page: https://huggingface.co/datasets/tasksource/oasst1_pairwise_rlhf_reward.

tasksource--oasst1-pairwise-rlhf-reward.parquet 500 rows tasksource/oasst1_pairwise_rlhf_reward

Open in Helix

Interesting queries to try

play_arrow distribution of lang
play_arrow most common values in parent_id
play_arrow summary charts for the Oasst1 Pairwise Rlhf Reward dataset
play_arrow top 10 rows of Oasst1 Pairwise Rlhf Reward with key statistics
play_arrow counts grouped by the most common field in Oasst1 Pairwise Rlhf Reward

Columns

lang categorical
parent_id text
prompt text
chosen text
rejected text