AI2 Adapt Dev

community

AI & ML interests

Open science can (maybe) save the world

Recent Activity

DongfuJiang authored a paper 5 days ago

EvolveCoder: Evolving Test Cases via Adversarial Verification for Code Reinforcement Learning

DongfuJiang authored a paper 5 days ago

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

DongfuJiang authored a paper 5 days ago

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

View all activity

ai2-adapt-dev 's datasets 187

ai2-adapt-dev/deepscaler_gt_with_random_max_length

Viewer • Updated Mar 18, 2025 • 40.3k • 3

ai2-adapt-dev/deepscaler_gt_random_max_length_only

Viewer • Updated Mar 18, 2025 • 40.3k • 4

ai2-adapt-dev/eurus2_random_max_length_only

Viewer • Updated Mar 11, 2025 • 455k • 3

ai2-adapt-dev/Wildchat-prefs-280824-olmoe

Viewer • Updated Mar 4, 2025 • 10.8k • 10

ai2-adapt-dev/s1k_1.1_messages

Viewer • Updated Feb 20, 2025 • 1k • 3

ai2-adapt-dev/rlvr_open_reasoner_math

Viewer • Updated Feb 20, 2025 • 56.9k • 9

ai2-adapt-dev/s1k_math_only_pref

Updated Feb 13, 2025 • 3

ai2-adapt-dev/helpsteer2-pref-subsamples

Updated Feb 10, 2025 • 14

ai2-adapt-dev/s1k_messages

Viewer • Updated Feb 7, 2025 • 1k • 3

ai2-adapt-dev/multipref-gpt4-overall-binarized

Viewer • Updated Feb 6, 2025 • 10.5k • 5

ai2-adapt-dev/multipref-human-overall-binarized

Viewer • Updated Feb 6, 2025 • 10.5k • 4

ai2-adapt-dev/s1k_math_parsed_only

Viewer • Updated Feb 4, 2025 • 624 • 14

ai2-adapt-dev/gsm8k

Viewer • Updated Jan 31, 2025 • 8.79k • 14

ai2-adapt-dev/numinamath_tir_ground_truth_one_turn

Viewer • Updated Jan 10, 2025 • 72.4k • 3

ai2-adapt-dev/math_ground_truth_with_hints

Viewer • Updated Jan 10, 2025 • 15k • 3

ai2-adapt-dev/eurus2_sft_converted

Viewer • Updated Jan 9, 2025 • 230k • 6

ai2-adapt-dev/eurus2_ground_truth_with_system

Viewer • Updated Jan 8, 2025 • 456k • 3

ai2-adapt-dev/eurus2_ground_truth

Viewer • Updated Jan 6, 2025 • 456k • 6

ai2-adapt-dev/instruction_tags_converted

Viewer • Updated Dec 28, 2024 • 60.7k • 4

ai2-adapt-dev/instruction_tags_human_labeled

Viewer • Updated Dec 28, 2024 • 14.4k • 3

ai2-adapt-dev/tulu-3-sft-downsample-0.05

Viewer • Updated Dec 19, 2024 • 47.2k • 4

ai2-adapt-dev/personahub_personas

Viewer • Updated Dec 19, 2024 • 243k • 3 • 1

ai2-adapt-dev/flanv2_styled

Viewer • Updated Nov 30, 2024 • 90k • 4

ai2-adapt-dev/flan_tulu_3_dpo_rs_verified

Viewer • Updated Nov 30, 2024 • 23.6k • 3

ai2-adapt-dev/flan_tulu_3_sft_rs_verified

Viewer • Updated Nov 30, 2024 • 17.9k • 4

ai2-adapt-dev/math_tulu_3_sft_rs_verified

Viewer • Updated Nov 29, 2024 • 15.5k • 2

ai2-adapt-dev/flanv2_ground_truth_90k

Viewer • Updated Nov 28, 2024 • 90k • 3

ai2-adapt-dev/ifeval_tulu_3_dpo_rs_verified

Viewer • Updated Nov 28, 2024 • 98.2k • 3

ai2-adapt-dev/ifeval_tulu_3_sft_rs_verified

Viewer • Updated Nov 28, 2024 • 80.4k • 2

ai2-adapt-dev/math_tulu_3_dpo_rs_verified

Viewer • Updated Nov 28, 2024 • 48.6k