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 • 214 • 1 -
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-2k
Text Generation • 2B • Updated • 118 -
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-4k
Text Generation • 2B • Updated • 109 -
Shiyu-Lab/QwQ-32B-thinkprune-4k
Text Generation • 33B • Updated • 8
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 • 214 • 1 -
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-2k
Text Generation • 2B • Updated • 118 -
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-4k
Text Generation • 2B • Updated • 109 -
Shiyu-Lab/QwQ-32B-thinkprune-4k
Text Generation • 33B • Updated • 8
models
30
Shiyu-Lab/HarnessLLM_SFT_Llama3_3B
4B
•
Updated
•
2
Shiyu-Lab/Inputoutput_SFT_Llama3_3B
4B
•
Updated
•
4
Shiyu-Lab/Inputoutput_SFT_Qwen3_4B
4B
•
Updated
•
4
Shiyu-Lab/HarnessLLM_SFT_Qwen3_4B
4B
•
Updated
•
17
Shiyu-Lab/Inputoutput_RL_Llama3_3B
4B
•
Updated
•
7
Shiyu-Lab/HarnessLLM_RL_Llama3_3B
4B
•
Updated
•
4
Shiyu-Lab/Inputoutput_RL_Qwen3_4B
4B
•
Updated
•
58
Shiyu-Lab/HarnessLLM_RL_Qwen3_4B
4B
•
Updated
•
64
Shiyu-Lab/QwQ-32B-thinkprune-iter2k
Text Generation
•
33B
•
Updated
•
30
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-3k
Text Generation
•
2B
•
Updated
•
7
datasets
12
Shiyu-Lab/Testcase_eval_data
Viewer
•
Updated
•
215
•
80
Shiyu-Lab/Testcase_RL_Data
Viewer
•
Updated
•
12k
•
130
Shiyu-Lab/Inputoutput_SFT_Data
Viewer
•
Updated
•
15.6k
•
45
Shiyu-Lab/HarnessLLM_SFT_Data
Viewer
•
Updated
•
15.6k
•
35
Shiyu-Lab/Testcase_MBPPHard
Viewer
•
Updated
•
141
•
26
Shiyu-Lab/Testcase_CF_Seen
Viewer
•
Updated
•
100
•
31
Shiyu-Lab/Testcase_CF_Unseen
Viewer
•
Updated
•
84
•
43
Shiyu-Lab/Testcase_LCB_Unseen
Viewer
•
Updated
•
93
•
44
Shiyu-Lab/Testcase_LCB_Seen
Viewer
•
Updated
•
76
•
24
Shiyu-Lab/C4-contrastive-watermark
Viewer
•
Updated
•
8.7k
•
27