Daman
daman1209arora
AI & ML interests
None yet
Recent Activity
liked a model 15 days ago
sfanm/unified-training upvoted a paper 25 days ago
Training Language Models to Fail Gracefully updated a collection about 1 month ago
graceful-failure-minesweeperOrganizations
graceful-failure-llm
Checkpoints containing Qwen3-1.7B-Base and Qwen3-4B-Base models using RLCR and GracefulRL.
-
daman1209arora/Reliability-1.7B-final-brier-ckpt-300
Text Generation • 2B • Updated • 6 -
daman1209arora/Reliability-1.7B-final-brier-ckpt-900
Text Generation • 2B • Updated • 7 -
daman1209arora/Reliability-1.7B-final-brier-ckpt-1500
Text Generation • 2B • Updated • 8 -
daman1209arora/Reliability-1.7B-final-brier-ckpt-1200
Text Generation • 2B • Updated • 7
graceful-failure-minesweeper
graceful-failure-llm
Checkpoints containing Qwen3-1.7B-Base and Qwen3-4B-Base models using RLCR and GracefulRL.
-
daman1209arora/Reliability-1.7B-final-brier-ckpt-300
Text Generation • 2B • Updated • 6 -
daman1209arora/Reliability-1.7B-final-brier-ckpt-900
Text Generation • 2B • Updated • 7 -
daman1209arora/Reliability-1.7B-final-brier-ckpt-1500
Text Generation • 2B • Updated • 8 -
daman1209arora/Reliability-1.7B-final-brier-ckpt-1200
Text Generation • 2B • Updated • 7
models 59
daman1209arora/Qwen3-4B-Minesweeper-GracefulRL-Grace0.75
4B • Updated • 7
daman1209arora/Qwen3-4B-Minesweeper-GracefulRL-Grace0.5
4B • Updated • 9
daman1209arora/Qwen3-4B-Minesweeper-GracefulRL-Grace0.25
4B • Updated • 8
daman1209arora/Qwen3-4B-Minesweeper-GracefulRL-Grace0
4B • Updated • 7
daman1209arora/Reliability-1.7B-final-idk-ckpt-1500
2B • Updated • 15
daman1209arora/Reliability-1.7B-final-idk-ckpt-1200
2B • Updated • 8
daman1209arora/Reliability-1.7B-final-idk-ckpt-900
2B • Updated • 7
daman1209arora/Reliability-1.7B-final-idk-ckpt-600
2B • Updated • 7
daman1209arora/Reliability-1.7B-final-idk-ckpt-300
2B • Updated • 7
daman1209arora/Reliability-1.7B-final-brier-ckpt-1500
Text Generation • 2B • Updated • 8
datasets 9
daman1209arora/qwen3_4b_idk_final
Viewer • Updated • 288k • 14
daman1209arora/bigmath
Viewer • Updated • 242k • 32
daman1209arora/11x11k_1000k
Updated • 24
daman1209arora/17x17k_1000k
Updated • 5
daman1209arora/maze_nb
Updated • 26
daman1209arora/jeebench_numeric
Viewer • Updated • 137 • 76
daman1209arora/dapo_subsampled
Updated • 3
daman1209arora/compression_dataset
Preview • Updated • 64 • 1
daman1209arora/jeebench
Viewer • Updated • 515 • 1.96k • 8