xuxin

xx18's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated 13 models 12 days ago

xx18/TFPI-Qwen3-4B-Thinking-2507-Stage3

Text Generation • 4B • Updated 12 days ago • 7

xx18/DirectRL_Qwen3-4B_baseline2

Text Generation • 4B • Updated 12 days ago • 10

xx18/DirectRL_Qwen3-4B_baseline1

Text Generation • 4B • Updated 12 days ago • 17

xx18/TFPI-Qwen3-4B-Stage3_then_RL

Text Generation • 4B • Updated 12 days ago • 13

xx18/TFPI-Qwen3-4B-Stage3

Text Generation • 4B • Updated 12 days ago • 14

xx18/TFPI-Qwen3-4B-Stage2

Text Generation • 4B • Updated 12 days ago • 10

xx18/TFPI-Qwen3-4B-Stage1

Text Generation • 4B • Updated 12 days ago • 9

xx18/DirectRL_DeepSeek-Qwen-1.5B_baseline2

Text Generation • 2B • Updated 12 days ago • 11

xx18/DirectRL_DeepSeek-Qwen-1.5B_baseline1

Text Generation • 2B • Updated 12 days ago • 6

xx18/TFPI-DeepSeek-Qwen-1.5B-Stage3_then_RL

Text Generation • 2B • Updated 12 days ago • 6

xx18/TFPI-DeepSeek-Qwen-1.5B-Stage3

Text Generation • 2B • Updated 12 days ago • 4

xx18/TFPI-DeepSeek-Qwen-1.5B-Stage2

Text Generation • 2B • Updated 12 days ago • 4

xx18/TFPI-DeepSeek-Qwen-1.5B-Stage1

Text Generation • 2B • Updated 12 days ago • 7

updated a collection 12 days ago

TFPI

Collection

Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners • 14 items • Updated 12 days ago

published a model 12 days ago

xx18/TFPI-Qwen3-4B-Thinking-2507-Stage3

Text Generation • 4B • Updated 12 days ago • 7

updated a collection 12 days ago

TFPI

Collection

Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners • 14 items • Updated 12 days ago