Magpie Alignment

community

AI & ML interests

Transparent LLM alignment for all.

Recent Activity

zhangchenxu authored a paper 25 days ago

VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL

zhangchenxu authored a paper about 1 month ago

TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning

yuchenlin authored a paper 3 months ago

CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation

View all activity

Magpie-Align 's datasets 44

Magpie-Align/Magpie-Reasoning-V1-150K

Viewer • Updated Jan 27 • 150k • 162 • 55

Magpie-Align/Magpie-Reasoning-V1-150K-CoT-Skywork-O1-Llama-3.1-8B

Viewer • Updated Jan 27 • 150k • 48 • 1

Magpie-Align/Magpie-Reasoning-V1-150K-CoT-QwQ

Viewer • Updated Jan 27 • 150k • 88 • 8

Magpie-Align/Magpie-Reasoning-V2-250K-CoT-Llama3

Viewer • Updated Jan 27 • 250k • 105 • 10

Magpie-Align/Magpie-Reasoning-V2-250K-CoT-Skywork-O1-Llama-3.1-8B

Viewer • Updated Jan 27 • 250k • 100 • 5

Magpie-Align/Magpie-Reasoning-V2-250K-CoT-QwQ

Viewer • Updated Jan 27 • 250k • 97 • 17

Magpie-Align/Magpie-Reasoning-V2-250K-CoT-Deepseek-R1-Llama-70B

Viewer • Updated Jan 27 • 250k • 630 • 99

Magpie-Align/Magpie-Reasoning-V1-150K-CoT-Deepseek-R1-Llama-70B

Viewer • Updated Jan 27 • 150k • 118 • 17

Magpie-Align/Magpie-Qwen2.5-Coder-Pro-300K-v0.1

Viewer • Updated Jan 13 • 300k • 97 • 4

Magpie-Align/Magpie-Qwen2.5-Math-Pro-300K-v0.1

Viewer • Updated Jan 13 • 300k • 55 • 1

Magpie-Align/Magpie-Qwen2.5-Pro-1M-v0.1

Viewer • Updated Jan 13 • 1M • 447 • 18

Magpie-Align/Magpie-Llama-3.3-Pro-1M-v0.1

Viewer • Updated Jan 2 • 1M • 215 • 1

Magpie-Align/Magpie-Llama-3.3-Pro-500K-Filtered

Viewer • Updated Jan 2 • 500k • 42 • 1

Magpie-Align/MagpieLM-DPO-Data-v0.1

Viewer • Updated Dec 9, 2024 • 200k • 102 • 16

Magpie-Align/MagpieLM-SFT-Data-v0.1

Viewer • Updated Dec 9, 2024 • 550k • 137 • 16

Magpie-Align/Magpie-100K-Generator-Zoo

Viewer • Updated Dec 9, 2024 • 100k • 37 • 2

Magpie-Align/Magpie-Qwen2.5-Pro-300K-Filtered

Viewer • Updated Oct 20, 2024 • 300k • 142 • 12

Magpie-Align/Magpie-Pro-MT-300K-v0.1

Viewer • Updated Aug 28, 2024 • 300k • 248 • 31

Magpie-Align/Magpie-Pro-300K-Filtered

Viewer • Updated Aug 28, 2024 • 300k • 563 • 45

Magpie-Align/Magpie-Llama-3.1-Pro-500K-Filtered

Viewer • Updated Aug 28, 2024 • 500k • 60 • 9

Magpie-Align/Magpie-Llama-3.1-Pro-300K-Filtered

Viewer • Updated Aug 28, 2024 • 300k • 247 • 13

Magpie-Align/Magpie-Llama-3.1-Pro-1M-v0.1

Viewer • Updated Aug 28, 2024 • 1M • 171 • 13

Magpie-Align/Magpie-Llama-3.1-Pro-MT-300K-Filtered

Viewer • Updated Aug 28, 2024 • 300k • 151 • 15

Magpie-Align/Magpie-Llama-3.1-Pro-MT-500K-v0.1

Viewer • Updated Aug 28, 2024 • 500k • 61 • 4

Magpie-Align/Magpie-Llama-3.1-Pro-DPO-100K-v0.1

Viewer • Updated Aug 22, 2024 • 100k • 149 • 5

Magpie-Align/Magpie-Qwen2-Pro-200K-Chinese

Viewer • Updated Aug 22, 2024 • 200k • 385 • 76

Magpie-Align/Llama-3-Magpie-Air-3M-v0.1

Viewer • Updated Aug 21, 2024 • 3M • 92 • 6

Magpie-Align/Magpie-Pro-DPO-100K-v0.1

Viewer • Updated Aug 21, 2024 • 100k • 62 • 8

Magpie-Align/Llama-3-Magpie-Pro-1M-v0.1

Viewer • Updated Aug 21, 2024 • 1M • 373 • 19

Magpie-Align/Magpie-DPO-100K-SML

Viewer • Updated Aug 20, 2024 • 82.5k • 42 • 5