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 • 343 • 1 -
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-2k
Text Generation • 2B • Updated • 114 -
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-4k
Text Generation • 2B • Updated • 105 -
Shiyu-Lab/QwQ-32B-thinkprune-4k
Text Generation • 33B • Updated • 3
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 • 343 • 1 -
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-2k
Text Generation • 2B • Updated • 114 -
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-4k
Text Generation • 2B • Updated • 105 -
Shiyu-Lab/QwQ-32B-thinkprune-4k
Text Generation • 33B • Updated • 3
models
30
Shiyu-Lab/HarnessLLM_SFT_Llama3_3B
4B
•
Updated
•
1
Shiyu-Lab/Inputoutput_SFT_Llama3_3B
4B
•
Updated
•
2
Shiyu-Lab/Inputoutput_SFT_Qwen3_4B
4B
•
Updated
•
2
Shiyu-Lab/HarnessLLM_SFT_Qwen3_4B
4B
•
Updated
•
107
Shiyu-Lab/Inputoutput_RL_Llama3_3B
4B
•
Updated
•
4
Shiyu-Lab/HarnessLLM_RL_Llama3_3B
4B
•
Updated
•
2
Shiyu-Lab/Inputoutput_RL_Qwen3_4B
4B
•
Updated
•
57
Shiyu-Lab/HarnessLLM_RL_Qwen3_4B
4B
•
Updated
•
68
Shiyu-Lab/QwQ-32B-thinkprune-iter2k
Text Generation
•
33B
•
Updated
•
26
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-3k
Text Generation
•
2B
•
Updated
•
4
datasets
12
Shiyu-Lab/Testcase_eval_data
Viewer
•
Updated
•
215
•
91
Shiyu-Lab/Testcase_RL_Data
Viewer
•
Updated
•
12k
•
171
Shiyu-Lab/Inputoutput_SFT_Data
Viewer
•
Updated
•
15.6k
•
48
Shiyu-Lab/HarnessLLM_SFT_Data
Viewer
•
Updated
•
15.6k
•
35
Shiyu-Lab/Testcase_MBPPHard
Viewer
•
Updated
•
141
•
30
Shiyu-Lab/Testcase_CF_Seen
Viewer
•
Updated
•
100
•
32
Shiyu-Lab/Testcase_CF_Unseen
Viewer
•
Updated
•
84
•
45
Shiyu-Lab/Testcase_LCB_Unseen
Viewer
•
Updated
•
93
•
45
Shiyu-Lab/Testcase_LCB_Seen
Viewer
•
Updated
•
76
•
27
Shiyu-Lab/C4-contrastive-watermark
Viewer
•
Updated
•
8.7k
•
22