AI & ML interests
None yet
Organizations
zijianh/DeepScaleR-1.5B-Preview-4096-step-0_05-0_1-270
2B
•
Updated
•
5
zijianh/DeepScaleR-1.5B-Preview-4096-step-0_05-0_1-180
2B
•
Updated
•
5
zijianh/DeepScaleR-1.5B-Preview-4096-step-0_1-260
2B
•
Updated
•
4
zijianh/DeepScaleR-1.5B-Preview-4096-step-0_1-100
2B
•
Updated
•
4
zijianh/DeepScaleR-1.5B-Preview-4096-step-0_1-40
2B
•
Updated
•
3
zijianh/DeepScaleR-1.5B-Preview-4096-range-0_1-new-140
2B
•
Updated
•
4
zijianh/DeepScaleR-1.5B-Preview-4096-range-0_1-new-70
2B
•
Updated
•
3
zijianh/DeepScaleR-1.5B-Preview-5120-sigmoid-0_1-30
2B
•
Updated
•
4
zijianh/DeepScaleR-1.5B-Preview-5120-sigmoid-0_1-40
2B
•
Updated
•
3
zijianh/DeepScaleR-1.5B-Preview-4096-range-0_1-260
2B
•
Updated
•
4
zijianh/grpo_NuminaMath-CoT-qwen2.5-1.5b-instruct_kl-clamp-250
2B
•
Updated
•
4
zijianh/grpo_gold_NuminaMath-CoT_gold_0-2-qwen2.5-1.5b-instruct-300
2B
•
Updated
•
2
zijianh/grpo_gold_NuminaMath-CoT_gold_0-2-qwen2.5-1.5b-instruct-200
2B
•
Updated
•
3
zijianh/grpo_gold_NuminaMath-CoT_gold_0-2-qwen2.5-1.5b-instruct-100
2B
•
Updated
•
3
zijianh/grpo_gold_NuminaMath-CoT_gold_0-1-qwen2.5-1.5b-instruct-200
2B
•
Updated
•
3
zijianh/grpo_gold_NuminaMath-CoT_gold_0-1-qwen2.5-1.5b-instruct-100
2B
•
Updated
•
3
zijianh/DeepScaleR-1.5B-Preview-4096-multi-objective-3level-0_1-0_5-450
2B
•
Updated
•
4
zijianh/DeepSeek-R1-Distill-Qwen-1.5B-4096-multi-objective-3level-0_1-0_5-570
2B
•
Updated
•
3
zijianh/DeepSeek-R1-Distill-Qwen-1.5B-4096-multi-objective-3level-300
2B
•
Updated
•
4
zijianh/DeepSeek-R1-Distill-Qwen-7B-4k-40
8B
•
Updated
•
4
zijianh/DeepSeek-R1-Distill-Qwen-7B-4k-30
8B
•
Updated
•
4
zijianh/DeepSeek-R1-Distill-Qwen-7B-4k-140
8B
•
Updated
•
3
zijianh/DeepSeek-R1-Distill-Qwen-7B-4k-100
8B
•
Updated
•
5
zijianh/DeepSeek-R1-Distill-Qwen-7B-4k-10
8B
•
Updated
•
4
zijianh/DeepSeek-R1-Distill-Qwen-7B-4k-50
8B
•
Updated
•
2
zijianh/DeepSeek-R1-Distill-Qwen-7B-2k-200
2B
•
Updated
•
4
zijianh/DeepSeek-R1-Distill-Qwen-7B-4k-220
8B
•
Updated
•
7
zijianh/DeepSeek-R1-Distill-Qwen-7B-4k-180
8B
•
Updated
•
5
zijianh/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-40k
2B
•
Updated
•
6
zijianh/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-220k
2B
•
Updated
•
5