AI & ML interests
None defined yet.
Recent Activity
View all 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 • 44 • 1 -
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-2k
Text Generation • 2B • Updated • 1 -
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-4k
Text Generation • 2B • Updated • 2 -
Shiyu-Lab/QwQ-32B-thinkprune-4k
Text Generation • 33B • Updated • 1
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 • 44 • 1 -
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-2k
Text Generation • 2B • Updated • 1 -
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-4k
Text Generation • 2B • Updated • 2 -
Shiyu-Lab/QwQ-32B-thinkprune-4k
Text Generation • 33B • Updated • 1
models 30
Shiyu-Lab/HarnessLLM_SFT_Llama3_3B
4B • Updated
Shiyu-Lab/Inputoutput_SFT_Llama3_3B
4B • Updated
Shiyu-Lab/Inputoutput_SFT_Qwen3_4B
4B • Updated
• 243
Shiyu-Lab/HarnessLLM_SFT_Qwen3_4B
4B • Updated
• 809
Shiyu-Lab/Inputoutput_RL_Llama3_3B
4B • Updated
• 1
Shiyu-Lab/HarnessLLM_RL_Llama3_3B
4B • Updated
Shiyu-Lab/Inputoutput_RL_Qwen3_4B
4B • Updated
Shiyu-Lab/HarnessLLM_RL_Qwen3_4B
4B • Updated
Shiyu-Lab/QwQ-32B-thinkprune-iter2k
Text Generation • 33B • Updated
• 2
Shiyu-Lab/DeepSeek-R1-Distill-Qwen-1.5B-thinkprune-3k
Text Generation • 2B • Updated
• 1
datasets 14
Shiyu-Lab/WebArena_video_demo
Viewer
• Updated
• 3.69k • 13
Shiyu-Lab/OSWorld_video_demo
Preview
• Updated
• 13
Shiyu-Lab/Testcase_eval_data
Viewer
• Updated
• 215 • 50
Shiyu-Lab/Testcase_RL_Data
Viewer
• Updated
• 12k • 48
Shiyu-Lab/Inputoutput_SFT_Data
Viewer
• Updated
• 15.6k • 14
Shiyu-Lab/HarnessLLM_SFT_Data
Viewer
• Updated
• 15.6k • 13
Shiyu-Lab/Testcase_MBPPHard
Viewer
• Updated
• 141 • 18
Shiyu-Lab/Testcase_CF_Seen
Viewer
• Updated
• 100 • 13
Shiyu-Lab/Testcase_CF_Unseen
Viewer
• Updated
• 84 • 17
Shiyu-Lab/Testcase_LCB_Unseen
Viewer
• Updated
• 93 • 19