DeepTheorem A dataset and RL-zero pipeline for advanced mathematical reasoning of informal theorem proving. Jiahao004/DeepTheorem Viewer • Updated Jul 3, 2025 • 121k • 163 • 25 Jiahao004/DeepTheorem-qwen-1.5b-rl 2B • Updated May 26, 2025 • 6 • 1 Jiahao004/DeepTheorem-qwen-3b-rl 3B • Updated May 26, 2025 • 13 Jiahao004/DeepTheorem-qwen-7b-rl 8B • Updated May 26, 2025 • 7 • 3
DeepTheorem A dataset and RL-zero pipeline for advanced mathematical reasoning of informal theorem proving. Jiahao004/DeepTheorem Viewer • Updated Jul 3, 2025 • 121k • 163 • 25 Jiahao004/DeepTheorem-qwen-1.5b-rl 2B • Updated May 26, 2025 • 6 • 1 Jiahao004/DeepTheorem-qwen-3b-rl 3B • Updated May 26, 2025 • 13 Jiahao004/DeepTheorem-qwen-7b-rl 8B • Updated May 26, 2025 • 7 • 3
