suu

Suu's activity

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

upvoted a collection 23 days ago

AEPO

Collection

The official datasets and model checkpoints of AEPO • 4 items • Updated 19 days ago • 3

upvoted a paper 23 days ago

Agentic Entropy-Balanced Policy Optimization

Paper • 2510.14545 • Published 24 days ago • 101

updated a collection about 1 month ago

KlearReasoner-8B

Collection

KlearReasoner-8B • 6 items • Updated 22 days ago • 3

updated a model about 1 month ago

Kwai-Klear/Klear-Reasoner-8B-SFT

8B • Updated Sep 27 • 6 • 2

updated 2 datasets about 1 month ago

Kwai-Klear/KlearReasoner-CodeSub-15K

Viewer • Updated Sep 27 • 15k • 201 • 4

Kwai-Klear/KlearReasoner-MathSub-30K

Viewer • Updated Sep 27 • 30k • 124 • 2

updated a model about 1 month ago

Kwai-Klear/Klear-Reasoner-8B

8B • Updated Sep 27 • 15 • 16

authored a paper about 1 month ago

CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning

Paper • 2509.20712 • Published Sep 25 • 18

upvoted a paper about 1 month ago

CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning

Paper • 2509.20712 • Published Sep 25 • 18

commented 3 papers about 1 month ago

CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning

Paper • 2509.20712 • Published Sep 25 • 18 •

4

CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning

Paper • 2509.20712 • Published Sep 25 • 18 •

4

CE-GPPO: Controlling Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning

Paper • 2509.20712 • Published Sep 25 • 18 •

4

upvoted a paper about 2 months ago

Finedeep: Mitigating Sparse Activation in Dense LLMs via Multi-Layer Fine-Grained Experts

Paper • 2502.12928 • Published Feb 18 • 1

liked a model about 2 months ago

Kwai-Klear/Klear-Reasoner-8B-SFT

8B • Updated Sep 27 • 6 • 2

New activity in Kwai-Klear/Klear-Reasoner-8B about 2 months ago

Improve model card: Add pipeline tag, library name, code/project links, and sample usage

1

#1 opened 3 months ago by

nielsr

请问评测结果是64K max_new_token下吗？

1

#2 opened 2 months ago by

JjjjjZzz

updated a collection 2 months ago

KlearReasoner-8B

Collection

KlearReasoner-8B • 6 items • Updated 22 days ago • 3

updated 2 models 2 months ago

Kwai-Klear/Klear-46B-A2.5B-Instruct

Text Generation • 46B • Updated Sep 7 • 111 • 81

Kwai-Klear/Klear-46B-A2.5B-Base

Text Generation • 46B • Updated Sep 7 • 23 • 28

liked a model 2 months ago

Kwai-Klear/Klear-46B-A2.5B-Instruct

Text Generation • 46B • Updated Sep 7 • 111 • 81