The official datasets and model checkpoints of ARPO
KABI
dongguanting
AI & ML interests
Reasoning and Alignment for Large Language Models
Recent Activity
upvoted
a
collection
1 day ago
RL+reason model
upvoted
a
paper
4 days ago
RecGPT Technical Report
upvoted
a
paper
5 days ago
Seed-Prover: Deep and Broad Reasoning for Automated Theorem Proving
Organizations
-
Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
Paper • 2505.16410 • Published • 57 -
dongguanting/Tool-Star-SFT-54K
Viewer • Updated • 54k • 230 • 7 -
dongguanting/Multi-Tool-RL-10K
Viewer • Updated • 10k • 112 • 3 -
dongguanting/Tool-Star-Qwen-7B
Text Generation • 8B • Updated • 545 • 2
The official datasets and model checkpoints of ARPO
-
Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning
Paper • 2505.16410 • Published • 57 -
dongguanting/Tool-Star-SFT-54K
Viewer • Updated • 54k • 230 • 7 -
dongguanting/Multi-Tool-RL-10K
Viewer • Updated • 10k • 112 • 3 -
dongguanting/Tool-Star-Qwen-7B
Text Generation • 8B • Updated • 545 • 2
models
10
dongguanting/Qwen2.5-7B-ARPO
Text Generation
•
8B
•
Updated
•
28
•
2
dongguanting/Qwen3-14B-ARPO-DeepSearch
15B
•
Updated
•
12
•
3
dongguanting/Qwen3-8B-ARPO-DeepSearch
8B
•
Updated
•
10
•
1
dongguanting/Llama3.1-8B-ARPO
8B
•
Updated
•
4
•
1
dongguanting/Qwen2.5-3B-ARPO
3B
•
Updated
•
30
•
1
dongguanting/Tool-Star-Qwen-7B
Text Generation
•
8B
•
Updated
•
545
•
2
dongguanting/RAG-Critic-3B
Text Generation
•
3B
•
Updated
•
10
•
1
dongguanting/Tool-Star-Qwen-0.5B
Text Generation
•
0.6B
•
Updated
•
10
•
1
dongguanting/Tool-Star-Qwen-1.5B
Text Generation
•
2B
•
Updated
•
5
•
2
dongguanting/Tool-Star-Qwen-3B
Text Generation
•
3B
•
Updated
•
208
•
5
datasets
11
dongguanting/ARPO-RL-DeepSearch-1K
Viewer
•
Updated
•
1.07k
•
174
•
2
dongguanting/ARPO-RL-Reasoning-10K
Viewer
•
Updated
•
10k
•
162
•
1
dongguanting/ARPO-SFT-54K
Viewer
•
Updated
•
54.6k
•
355
•
7
dongguanting/RAG-Error-Critic-100K
Viewer
•
Updated
•
100k
•
28
•
2
dongguanting/Tool-Star-SFT-54K
Viewer
•
Updated
•
54k
•
230
•
7
dongguanting/Multi-Tool-RL-10K
Viewer
•
Updated
•
10k
•
112
•
3
dongguanting/RAG-QA-40K
Viewer
•
Updated
•
32.8k
•
24
•
2
dongguanting/ShareGPT-12K
Viewer
•
Updated
•
12.9k
•
11
•
1
dongguanting/VIF-RAG-QA-110K
Viewer
•
Updated
•
111k
•
32
•
7
dongguanting/DotamathQA
Viewer
•
Updated
•
574k
•
42
•
2