arxiv:2305.15074
Daman
daman1209arora
AI & ML interests
None yet
Organizations
models 37
daman1209arora/alpha_0.2_DeepSeek-R1-Distill-Qwen-7B
Text Generation • 8B • Updated • 8
daman1209arora/MaxRL-Qwen3-1.7B-Base-IDK-math12k-32-brier-rloo-step2000
2B • Updated • 1
daman1209arora/tailrl_1900_math12k
2B • Updated • 2
daman1209arora/mpi_n5_colm
0.6B • Updated • 3
daman1209arora/16M_ckpt-6000
15.8M • Updated • 2
daman1209arora/sft_1M_ckpt_6000
993k • Updated • 2
daman1209arora/sft_16M_ckpt-6000
15.8M • Updated • 3
daman1209arora/mpi_async_n4
0.6B • Updated • 3
daman1209arora/mpi_async_n3
0.6B • Updated • 1
daman1209arora/mpi_async_n2
0.6B • Updated • 1
datasets 7
daman1209arora/11x11k_1000k
Updated • 27
daman1209arora/17x17k_1000k
Updated • 48
daman1209arora/maze_nb
Updated • 53
daman1209arora/jeebench_numeric
Viewer • Updated • 137 • 13
daman1209arora/dapo_subsampled
Updated • 54
daman1209arora/compression_dataset
Preview • Updated • 80 • 1
daman1209arora/jeebench
Viewer • Updated • 515 • 3.1k • 8