Deepseek Prover V1.5 SFT
DeepSeek develops Deepseek Prover V 1.5 SFT, a chat model exceling at reasoning and text generation, particularly in formal mathematical languages. It is notably trained using reinforcement learning from proof assistant feedback and employs a variant of Monte-Carlo tree search, achieving state-of-the-art results on the miniF2F and ProofNet benchmarks with scores of 63.5% and 25.3%, respectively.
Input
Output
Context
4K
Max Output
2K
Parameters
7B
Technical Specifications
Model TypeCode
Context Window4,000 tokens
Max Output Tokens2,048 tokens
Parameters7B
Release DateAug 15, 2024
Training CutoffNot available
Licenseother
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Deepseek Prover V1.5 SFT
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.