A collection of mini-swe-agent-plus and corresponding rollout traces that drive Qwen3-8B to a 39% solve rate on SWE-bench Verified. Enjoy!
AI & ML interests
LLM foundation&research @ Kuaishou Technology
Recent Activity
View all activity
Organization Card
Edit this README.md markdown file to author your organization card.
models
8
Kwai-Klear/Klear-AgentForge-8B
8B
•
Updated
•
2.9k
•
1
Kwai-Klear/Klear-AgentForge-8B-SFT
308k
•
Updated
•
1.56k
•
4
Kwai-Klear/Klear-Reasoner-8B-SFT
8B
•
Updated
•
20
•
2
Kwai-Klear/Klear-Reasoner-8B
8B
•
Updated
•
37
•
19
Kwai-Klear/Klear-46B-A2.5B-Base
Text Generation
•
46B
•
Updated
•
78
•
28
Kwai-Klear/Klear-46B-A2.5B-Instruct
Text Generation
•
46B
•
Updated
•
20
•
81
Kwai-Klear/Klear-Qwen3-Thinking-Preview
8B
•
Updated
•
15
•
2
Kwai-Klear/qwen2.5-math-rlep
Text Generation
•
8B
•
Updated
•
21
datasets
6
Kwai-Klear/SWE-smith-mini_swe_agent_plus-trajectories-66k
Viewer
•
Updated
•
66k
•
881
•
9
Kwai-Klear/KlearReasoner-CodeSub-15K
Viewer
•
Updated
•
15k
•
171
•
6
Kwai-Klear/KlearReasoner-MathSub-30K
Viewer
•
Updated
•
30k
•
89
•
3
Kwai-Klear/Klear-CodeTest
Viewer
•
Updated
•
24.7k
•
1.13k
Kwai-Klear/Klear-Qwen3-Thinking-Preview
Updated
•
6
Kwai-Klear/RLEP_dataset
Updated
•
208
•
1