arxiv:2508.01119
Saba Ahmadi
sabaa96
AI & ML interests
None yet
Organizations
models
32
sabaa96/imged_rl_mix_all_bigxmix_stage1_8000_rl_balanced_k8
Updated
sabaa96/imged_rl_mix_all_bigxmix_stage2_18400_rl_balanced_k8
Updated
sabaa96/reasoning_verbose-May3_got__256_1e-4_weightdecay0-stochastic-1.0-checkpoint-18000
8B
•
Updated
sabaa96/reasoning_verbose-May1_got__256_1e-4_weightdecay0-text-loss-0.2-checkpoint-4800
8B
•
Updated
•
1
sabaa96/reasoning_verbose-May1_got__256_1e-4_weightdecay0-stochastic-1.0-checkpoint-4800
8B
•
Updated
sabaa96/reasoning_verbose-May1_got__256_1e-4_weightdecay0-hybrid-exclusive-1.0-checkpoint-4800
8B
•
Updated
•
1
sabaa96/reasoning_verbose-May1_got__256_1e-4_weightdecay0-text-loss-0.2-checkpoint-15510
8B
•
Updated
•
1
sabaa96/reasoning_verbose-May1_got__256_1e-4_weightdecay0-stochastic-1.0-checkpoint-15510
8B
•
Updated
sabaa96/reasoning_verbose-May1_got__256_1e-4_weightdecay0-hybrid-exclusive-1.0-checkpoint-15510
8B
•
Updated
•
1
sabaa96/reasoning_verbose-May1_got__256_1e-4_weightdecay0-stochastic-1.0-checkpoint-9600
8B
•
Updated
•
2
datasets
0
None public yet