zijianh/grpo_NuminaMath-CoT-qwen2.5-1.5b-instruct_kl-clamp-250
Updated
•
7
Zijian Huang
zijianh
AI & ML interests
None yet
Recent Activity
updated
a model
11 days ago
zijianh/grpo_NuminaMath-CoT-qwen2.5-1.5b-instruct_kl-clamp-250
published
a model
11 days ago
zijianh/grpo_NuminaMath-CoT-qwen2.5-1.5b-instruct_kl-clamp-250
updated
a model
14 days ago
zijianh/grpo_gold_NuminaMath-CoT_gold_0-2-qwen2.5-1.5b-instruct-300
Organizations
models
42
zijianh/grpo_gold_NuminaMath-CoT_gold_0-2-qwen2.5-1.5b-instruct-300
Updated
•
23
zijianh/grpo_gold_NuminaMath-CoT_gold_0-2-qwen2.5-1.5b-instruct-200
Updated
•
35
zijianh/grpo_gold_NuminaMath-CoT_gold_0-2-qwen2.5-1.5b-instruct-100
Updated
•
40
zijianh/grpo_gold_NuminaMath-CoT_gold_0-1-qwen2.5-1.5b-instruct-200
Updated
•
11
zijianh/grpo_gold_NuminaMath-CoT_gold_0-1-qwen2.5-1.5b-instruct-100
Updated
•
25
zijianh/DeepScaleR-1.5B-Preview-4096-multi-objective-3level-0_1-0_5-450
Updated
zijianh/DeepSeek-R1-Distill-Qwen-1.5B-4096-multi-objective-3level-0_1-0_5-570
Updated
zijianh/DeepSeek-R1-Distill-Qwen-1.5B-4096-multi-objective-3level-300
Updated
zijianh/DeepSeek-R1-Distill-Qwen-7B-4k-40
Updated
datasets
0
None public yet