AMPO: adaptive multi-guidance policy optimization with diverse teacher models (arXiv:2510.02227)
EnigmaYYYY
SII-Enigma
AI & ML interests
SII is an institution dedicated to innovation in education and research in the field of AI.
Recent Activity
updated a dataset about 16 hours ago
SII-Enigma/Davinci-ToolData updated a model about 16 hours ago
SII-Enigma/Davinci-Tool-30B-SFT updated a model about 16 hours ago
SII-Enigma/Davinci-Tool-30BOrganizations
None yet
models 12
SII-Enigma/Davinci-Tool-30B-SFT
Text Generation • 211k • Updated • 293
SII-Enigma/Davinci-Tool-30B
Text Generation • 211k • Updated • 298
SII-Enigma/Llama3.2-8B-Ins-AMPO
Text Generation • 8B • Updated • 64
SII-Enigma/Qwen2.5-1.5B-Ins-AMPO
Text Generation • 2B • Updated • 30
SII-Enigma/Qwen2.5-7B-Ins-SFT-GRPO
Text Generation • 8B • Updated • 45
SII-Enigma/Qwen2.5-7B-Ins-SFT-AMPO-4S
8B • Updated • 10
SII-Enigma/Qwen2.5-7B-Ins-SFT-AMPO-4L
8B • Updated • 8
SII-Enigma/Qwen2.5-7B-Ins-AMPO
Text Generation • 8B • Updated • 47
SII-Enigma/Llama3.2-8B-Ins-GRPO
Text Generation • 2B • Updated • 19 • 1
SII-Enigma/Qwen2.5-7B-Ins-SFT-32k
Text Generation • 8B • Updated • 59 • 1
datasets 7
SII-Enigma/Davinci-ToolData
Viewer • Updated • 15.2k • 72
SII-Enigma/SFT-4LongCoTs-32k
Viewer • Updated • 32.3k • 15
SII-Enigma/OpenR1-Math-R1-8.5k
Viewer • Updated • 8.49k • 7
SII-Enigma/OpenR1-Math-4LongCoTs_4ShortCoTs-8.5k
Viewer • Updated • 8.49k • 8
SII-Enigma/OpenR1-Math-4ShortCoTs-8.5k
Viewer • Updated • 8.49k • 7
SII-Enigma/OpenR1-Math-4LongCoTs_R1-8.5k
Viewer • Updated • 8.49k • 16
SII-Enigma/OpenR1-Math-4LongCoTs-8.5k
Viewer • Updated • 8.49k • 15