SWY666/SimPO_adjusted_Best3_Qwen
3B • Updated • 1
Weiyu Sun
SWY666
·
AI & ML interests
Trustworthy AI, AI for Education, AI security, AI for health, Signal Processing
Organizations
SWY666/SimPO_adjusted_Best13_Qwen
3B • Updated
SWY666/SimPO_adjusted_Best3-2
Updated
SWY666/SimPO_adjusted_Best3
Updated
SWY666/SimPO_adjusted
Updated
SWY666/Qwen-2.5-7B-Simple-RL-with-reward-model-pure-debug
Updated
SWY666/Qwen-2.5-7B-Simple-RL-with-reward-model-pure
Updated
SWY666/Qwen-2.5-7B-Simple-RL-with-reward-model
Text Generation • 8B • Updated • 6
SWY666/Qwen-2.5-7B-Simple-RL-debug
Updated
SWY666/Qwen-2.5-7B-Simple-RL
Text Generation • 8B • Updated • 6
SWY666/gemma-2-2b-it
Text Generation • 3B • Updated • 5
SWY666/Qwen2.5-1.5B-Open-R1-GRPO
Updated
SWY666/DeepSeek-R1-Distill-Qwen-7B-GRPO
Updated