reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT
reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT is a 1.7 billion parameter Qwen3-based causal language model developed by Convergent Intelligence LLC. It was created through a two-stage process: knowledge distillation from a 30B Coder teacher for structured reasoning, followed by supervised fine-tuning on 54,600 logical inference problems. This model excels at formal logical inference, propositional logic, and STEM derivation, leveraging a 1024-token context length.
Loading preview...
Model Overview
This model, reaperdoesntknow/Qwen3-1.7B-Coder-Distilled-SFT, is a 1.7 billion parameter Qwen3-based language model developed by Convergent Intelligence LLC. It is specifically designed for logical inference and structured reasoning, built upon a unique two-stage training pipeline. The model's core strength lies in its ability to perform formal propositional logic and rigorous STEM derivations.
Key Capabilities
- Structured Reasoning Backbone: Achieved through knowledge distillation from a 30B Qwen3-Coder teacher model, transferring its precise sequential logic, explicit state tracking, and compositional decomposition patterns.
- Logical Inference: Fine-tuned on approximately 54,600 instruction-response pairs from the LogicInference dataset, covering propositional logic and formal inference.
- STEM Derivation: Capable of generating rigorous derivations for problems across 12 STEM domains, including Physics, Mathematics, and Engineering.
- Efficient Size: At 1.7B parameters, it offers specialized reasoning capabilities in a compact form factor, suitable for edge deployment (GGUF versions available).
Good For
- Logical inference and propositional logic tasks.
- Formal reasoning and structured argumentation.
- Generating rigorous STEM derivations.
- Educational tutoring applications.
- Component in verification pipelines.
- Edge deployment scenarios requiring specialized reasoning.