RyanYr/grpo-dapo_shuffled-01_offline-grpo-dapo-qwen3-4B-Base-mbs128-n4-mbs128-n4_mmlupro
收藏Hugging Face2026-04-27 更新2026-05-03 收录
下载链接:
https://hf-mirror.com/datasets/RyanYr/grpo-dapo_shuffled-01_offline-grpo-dapo-qwen3-4B-Base-mbs128-n4-mbs128-n4_mmlupro
下载链接
链接失效反馈官方服务:
资源简介:
---
dataset_info:
features:
- name: prompt
list:
- name: role
dtype: string
- name: content
dtype: string
- name: data_source
dtype: string
- name: reward_model
struct:
- name: ground_truth
dtype: string
- name: style
dtype: string
- name: responses
list: string
splits:
- name: test.100
num_bytes: 231708805
num_examples: 12032
- name: test.95
num_bytes: 243968820
num_examples: 12032
- name: test.90
num_bytes: 217943308
num_examples: 12032
- name: test.85
num_bytes: 215808086
num_examples: 12032
- name: test.80
num_bytes: 237950071
num_examples: 12032
- name: test.75
num_bytes: 209965318
num_examples: 12032
- name: test.70
num_bytes: 197447481
num_examples: 12032
- name: test.65
num_bytes: 192311519
num_examples: 12032
- name: test.60
num_bytes: 192452857
num_examples: 12032
- name: test.55
num_bytes: 304770263
num_examples: 12032
- name: test.50
num_bytes: 451768262
num_examples: 12032
- name: test.45
num_bytes: 482249139
num_examples: 12032
- name: test.40
num_bytes: 484943518
num_examples: 12032
- name: test.35
num_bytes: 457892092
num_examples: 12032
- name: test.30
num_bytes: 356593794
num_examples: 12032
- name: test.25
num_bytes: 317611429
num_examples: 12032
- name: test.20
num_bytes: 296365808
num_examples: 12032
- name: test.15
num_bytes: 199564144
num_examples: 12032
- name: test.10
num_bytes: 177593597
num_examples: 12032
download_size: 5463489926
dataset_size: 5468908311
configs:
- config_name: default
data_files:
- split: test.100
path: data/test.100-*
- split: test.95
path: data/test.95-*
- split: test.90
path: data/test.90-*
- split: test.85
path: data/test.85-*
- split: test.80
path: data/test.80-*
- split: test.75
path: data/test.75-*
- split: test.70
path: data/test.70-*
- split: test.65
path: data/test.65-*
- split: test.60
path: data/test.60-*
- split: test.55
path: data/test.55-*
- split: test.50
path: data/test.50-*
- split: test.45
path: data/test.45-*
- split: test.40
path: data/test.40-*
- split: test.35
path: data/test.35-*
- split: test.30
path: data/test.30-*
- split: test.25
path: data/test.25-*
- split: test.20
path: data/test.20-*
- split: test.15
path: data/test.15-*
- split: test.10
path: data/test.10-*
---
提供机构:
RyanYr



