Download
DeepSeek-Prover-V2 is DeepSeek’s specialized model for formal theorem proving, particularly targeting proof in Lean 4. The repository describes how they use recursive proof decomposition by prompting DeepSeek-V3 to break complex theorems into subgoals, synthesize proof sketches, and then combine them to bootstrap training data. They then fine-tune via reinforcement learning with binary correct/incorrect feedback to integrate informal reasoning with formal proof behavior. The repo releases two model sizes (7B and 671B) and provides evaluation performance (e.g. pass rates on MiniF2F, results on ProverBench) as well as prompt / usage examples for proof generation in Lean 4. It also includes a PDF of the paper or project overview and sample formalization datasets. Because theorem proving is a cutting-edge area in LLM research, Prover-V2 is positioned as a pushing-forward effort in formal reasoning for LLMs.
Features
- Formal theorem proving in Lean 4 with generated proof strategies
- Cold-start synthesis via recursive subgoal decomposition from V3
- Reinforcement learning fine-tuning with binary feedback for formal correctness
- Two released sizes: 7B and 671B models for different resource settings
- Benchmarking on MiniF2F and ProverBench for formal math problems
- Examples and usage scripts for prompting and proof generation
Project Samples
