AI & ML interests
None defined yet.
Recent Activity
ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning
-
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-iter2k
Text Generation • 2B • Updated • 181 • 1 -
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-2k
Text Generation • 2B • Updated • 119 -
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-4k
Text Generation • 2B • Updated • 82 -
Shiyu-Lab/QwQ-32B-thinkprune-4k
Text Generation • 33B • Updated • 9
ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning
-
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-iter2k
Text Generation • 2B • Updated • 181 • 1 -
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-2k
Text Generation • 2B • Updated • 119 -
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-4k
Text Generation • 2B • Updated • 82 -
Shiyu-Lab/QwQ-32B-thinkprune-4k
Text Generation • 33B • Updated • 9
models
30
Shiyu-Lab/HarnessLLM_SFT_Llama3_3B
4B
•
Updated
•
3
Shiyu-Lab/Inputoutput_SFT_Llama3_3B
4B
•
Updated
•
5
Shiyu-Lab/Inputoutput_SFT_Qwen3_4B
4B
•
Updated
•
5
Shiyu-Lab/HarnessLLM_SFT_Qwen3_4B
4B
•
Updated
•
18
Shiyu-Lab/Inputoutput_RL_Llama3_3B
4B
•
Updated
•
7
Shiyu-Lab/HarnessLLM_RL_Llama3_3B
4B
•
Updated
•
5
Shiyu-Lab/Inputoutput_RL_Qwen3_4B
4B
•
Updated
•
59
Shiyu-Lab/HarnessLLM_RL_Qwen3_4B
4B
•
Updated
•
65
Shiyu-Lab/QwQ-32B-thinkprune-iter2k
Text Generation
•
33B
•
Updated
•
7
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-3k
Text Generation
•
2B
•
Updated
•
9
datasets
12
Shiyu-Lab/Testcase_eval_data
Viewer
•
Updated
•
215
•
68
Shiyu-Lab/Testcase_RL_Data
Viewer
•
Updated
•
12k
•
113
Shiyu-Lab/Inputoutput_SFT_Data
Viewer
•
Updated
•
15.6k
•
37
Shiyu-Lab/HarnessLLM_SFT_Data
Viewer
•
Updated
•
15.6k
•
28
Shiyu-Lab/Testcase_MBPPHard
Viewer
•
Updated
•
141
•
17
Shiyu-Lab/Testcase_CF_Seen
Viewer
•
Updated
•
100
•
24
Shiyu-Lab/Testcase_CF_Unseen
Viewer
•
Updated
•
84
•
38
Shiyu-Lab/Testcase_LCB_Unseen
Viewer
•
Updated
•
93
•
38
Shiyu-Lab/Testcase_LCB_Seen
Viewer
•
Updated
•
76
•
18
Shiyu-Lab/C4-contrastive-watermark
Viewer
•
Updated
•
8.7k
•
74