DeepSeek-V1-and-V1.5-Series
-
deepseek-ai/DeepSeek-Prover-V1.5-Base
Updated • 325 • 6 -
deepseek-ai/DeepSeek-Prover-V1.5-SFT
Updated • 45 • 6 -
deepseek-ai/DeepSeek-Prover-V1.5-RL
Updated • 13.1k • 36 -
DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search
Paper • 2408.08152 • Published • 52