RLHFlow/UltraFeedback-preference-standard download history

RLHFlow/UltraFeedback-preference-standard is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 549 times (159 in the last 7 days), and 9,230 times in total. It ranks #30,834 among datasets by monthly downloads.

We include all the possible comparisons following the Instruct-GPT. We use the fine-grained_score. import os import matplotlib.pyplot as plt import numpy as np import pandas as pd from datasets import load_dataset, DatasetDict from transformers import AutoTokenizer from tqdm import tqdm from transf

Models trained on UltraFeedback-preference-standard

6 models list it as training data.

• mario-rc/multi-domain-rm-fsfairx-llama-3-8b-it 50 downloads in 30 days
• mario-rc/multi-domain-rm-fsfairx-gemma-2-9b-it 48 downloads in 30 days
• mario-rc/multi-domain-rm-skywork-llama-3.1-8b-it 40 downloads in 30 days
• mario-rc/multi-domain-rm-mistral-7b-it 36 downloads in 30 days
• mario-rc/multi-domain-rm-qwen-3-nemotron-8b-it 36 downloads in 30 days
• mario-rc/multi-domain-rm-skywork-qwen-3-8b-it 36 downloads in 30 days

Open RLHFlow/UltraFeedback-preference-standard on Hugging Face