AI2 Adapt Dev

community

AI & ML interests

Open science can (maybe) save the world

Recent Activity

DongfuJiang authored a paper 9 days ago

Critique-Coder: Enhancing Coder Models by Critique Reinforcement Learning

DongfuJiang authored a paper 9 days ago

VideoScore2: Think before You Score in Generative Video Evaluation

DongfuJiang authored a paper about 1 month ago

VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use

View all activity

ai2-adapt-dev 's datasets 279

ai2-adapt-dev/tool-use-refusals-v3.0

Viewer • Updated Jun 23 • 50k • 7

ai2-adapt-dev/tool-use-refusals-test

Viewer • Updated Jun 23 • 1k • 14

ai2-adapt-dev/tool-use-refusals-v2.1

Viewer • Updated Jun 23 • 50k • 9

ai2-adapt-dev/tool-use-refusals-v2.0

Viewer • Updated Jun 13 • 50k • 8

ai2-adapt-dev/toolu-sft-mix-T1-diverse-api-format

Viewer • Updated Jun 11 • 286k • 6

ai2-adapt-dev/toolu-sft-mix-T2-corrected

Viewer • Updated Jun 9 • 294k • 8

ai2-adapt-dev/toolu-sft-mix-T1-corrected

Viewer • Updated Jun 9 • 257k • 6

ai2-adapt-dev/tool-use-more-reasoning-v2-cleaned

Viewer • Updated Jun 9 • 53.3k • 10

ai2-adapt-dev/toolu-sft-mix-T1-unified-api-format

Viewer • Updated Jun 9 • 286k • 5

ai2-adapt-dev/T1-judgments

Viewer • Updated Jun 8 • 346k • 10

ai2-adapt-dev/toolu-sft-mix-T2-staging

Viewer • Updated Jun 8 • 326k • 6

ai2-adapt-dev/toolu-sft-mix-T1

Viewer • Updated Jun 7 • 286k • 7

ai2-adapt-dev/s2-archive-tooluse

Viewer • Updated Jun 6 • 266k • 8

ai2-adapt-dev/tool-use-refusals-v1.0

Viewer • Updated Jun 6 • 40k • 10

ai2-adapt-dev/toolu-synthetic-S1

Viewer • Updated Jun 6 • 226k • 5

ai2-adapt-dev/tool-use-ablation-multistep-60k-cleaned

Viewer • Updated Jun 6 • 60k • 11

ai2-adapt-dev/tool-use-ablation-multistep-60k

Viewer • Updated Jun 6 • 60k • 8

ai2-adapt-dev/tool-use-more-multistep-corrected

Viewer • Updated Jun 6 • 20k • 8

ai2-adapt-dev/tool-use-more-multistep

Viewer • Updated Jun 5 • 20k • 12

ai2-adapt-dev/tool-use-more-reasoning-v2

Viewer • Updated Jun 5 • 53.6k • 10

ai2-adapt-dev/tool-use-ablation-multiturn-60k

Viewer • Updated Jun 5 • 60k • 10

ai2-adapt-dev/tool-use-ablation-parallel-60k

Viewer • Updated Jun 5 • 60k • 9

ai2-adapt-dev/tool-use-ablation-vanilla-60k

Viewer • Updated Jun 5 • 60k • 6

ai2-adapt-dev/multi_step_reasoning_tool_use_4omini-cleaned

Viewer • Updated Jun 4 • 53.7k • 10

ai2-adapt-dev/multi_step_reasoning_tool_use_4omini

Viewer • Updated Jun 4 • 53.7k • 10

ai2-adapt-dev/toolu-sft-mix-v1

Viewer • Updated Jun 2 • 466k • 10

ai2-adapt-dev/interactive_tool_use_gpt4omini-v6-cleaned

Viewer • Updated Jun 2 • 99.5k • 7

ai2-adapt-dev/interactive_tool_use_gpt4omini-v6

Viewer • Updated May 29 • 99.8k • 11

ai2-adapt-dev/interactive_tool_use_gpt4omini-v5-cleaned

Viewer • Updated May 22 • 21.9k • 9

ai2-adapt-dev/interactive_tool_use_gpt4omini-v5

Viewer • Updated May 22 • 22k • 8