datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
SimpleRL-Zoo-Datasimplerl-minerva-mathsimplerl-OlympiadBenchSimple-RL-Zoo-Data-DeduplicatedSimpleRL-Zoosimple-rlhf-rmsimple-rlhf-rlsimplerlsimplerl-critique-offlinesimplerl_qwen_level1to4import re
import datasets
ds = datasets.load_dataset("hkust-nlp/SimpleRL-Zoo-Data",
data_files="simplelr_qwen_level1to4/train.parquet",
split="train")
def extract_user_content(content):
pattern = r'<\|im_start\|>user\n(.*?)<\|im_end\|>'
match = re.search(pattern, content, re.DOTALL)
if match:
return match.group(1).strip()
return None
def map_func(example):
content =… See the full description on the dataset page: https://huggingface.co/datasets/rasdani/simplerl_qwen_level1to4.simple_rl_level3to5simplerl-math8kSimpleRL-Zoo-Data-random-5Ksimplified_simplerl_qwen_level1to4SimpleRL-Zoo-CleanedSimple-RL-Zoo-Data-DeduplicatedQwen-2.5-Math-7B-SimpleRL-Zero-best_of_n-VLLM-Skywork-o1-Open-PRM-Qwen-2.5-7B-completionsSimpleRL-SFTinstruct_simplerl_qwen_level1to4Qwen-2.5-Math-7B-SimpleRL-best_of_n-VLLM-Skywork-o1-Open-PRM-Qwen-2.5-7B-completionsQwen-2.5-Math-7B-SimpleRL-best_of_n-VLLM-Skywork-o1-Open-PRM-Qwen-2.5-7B-completionscustomed_simplerl_hardmodified_simplerl_qwen_level1to4simple-rlhf-sftsimple_rl_level1to4simpleRL-codeQwen-2.5-Math-7B-SimpleRL-Zero-best_of_n-VLLM-Skywork-o1-Open-PRM-Qwen-2.5-7B-completionsQwen-2.5-14B-SimpleRL-Zoo-best_of_n-VLLM-Skywork-o1-Open-PRM-Qwen-2.5-7B-completionsQwen-2.5-32B-SimpleRL-Zoo-best_of_n-VLLM-Skywork-o1-Open-PRM-Qwen-2.5-7B-completionsSimple-RL-Data