StepFun Formalizer 7B
StepFun Formalizer 7B converts natural-language mathematical problems into formal Lean 4 statements. StepFun builds this specialist on DeepSeek-R1-Distill-Qwen-7B.
Research release
Supply the mathematical statement and header
The card's example provides the informal problem, a Lean header and a requested theorem name. This controls the shape of the generated declaration before any proof is attempted.StepFun StepFun-Formalizer-7B model card
Review whether the formal statement means the same thing
Practical guidance. Compilation alone cannot show that a generated statement preserves the original problem. Review domains, quantifiers, assumptions and inequality directions. A proof of a changed statement does not solve the intended problem.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | StepFun-Formalizer-7B |
| Base model | DeepSeek-R1-Distill-Qwen-7B.StepFun StepFun-Formalizer-7B model card |
| License | Apache 2.0 for code and model weights.StepFun StepFun-Formalizer-7B model card |
| Task | Formal statement generation; it does not replace a proof checker.StepFun StepFun-Formalizer-7B model card |
Related models
- StepFun Formalizer 32B
StepFun · StepFun Formalizer
A DeepSeek-R1-Distill-Qwen-32B-based model that converts mathematical text into Lean 4 statements.
Launch date not confirmedResearch releaseDownloadable - StepFun Prover Preview 7B
StepFun · StepFun Prover
StepFun Prover Preview 7B is a theorem-proving model derived from DeepSeek-R1-Distill-Qwen-7B.
Launch date not confirmedResearch releaseDownloadable