Magpie Alignment

community

magpie-align

AI & ML interests

Transparent LLM alignment for all.

Recent Activity

zhangchenxu authored a paper about 1 month ago

TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments

zhangchenxu authored a paper 5 months ago

VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL

zhangchenxu authored a paper 5 months ago

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

View all activity

Magpie-Align 's datasets 44

Magpie-Align/Magpie-Pro-DPO-200K

Viewer • Updated Aug 20, 2024 • 207k • 10 • 7

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

Viewer • Updated Aug 20, 2024 • 100k • 98 • 4

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

Viewer • Updated Aug 20, 2024 • 300k • 41 • 19

Magpie-Align/Llama-3-8B-Self-Instruct-100K

Viewer • Updated Aug 19, 2024 • 100k • 9 • 1

Magpie-Align/Magpie-Gemma2-Pro-200K-Filtered

Viewer • Updated Jul 22, 2024 • 200k • 17 • 15

Magpie-Align/Magpie-Gemma2-Pro-534K-v0.1

Viewer • Updated Jul 22, 2024 • 534k • 18 • 2

Magpie-Align/Magpie-Qwen-Air-300K-Filtered

Viewer • Updated Jul 5, 2024 • 300k • 21 • 3

Magpie-Align/Magpie-Qwen2-Air-3M-v0.1

Viewer • Updated Jul 5, 2024 • 3M • 65 • 6

Magpie-Align/Magpie-Air-300K-Filtered

Viewer • Updated Jul 3, 2024 • 300k • 49 • 5

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

Viewer • Updated Jul 3, 2024 • 300k • 247 • 1

Magpie-Align/Magpie-Phi3-Pro-300K-Filtered

Viewer • Updated Jul 3, 2024 • 300k • 49 • 6

Magpie-Align/Magpie-Phi3-Pro-1M-v0.1

Viewer • Updated Jul 3, 2024 • 1M • 41 • 4

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

Viewer • Updated Jul 3, 2024 • 200k • 56 • 9

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

Viewer • Updated Jul 3, 2024 • 1M • 61 • 14