---
license: apache-2.0
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
tags:
- reinforcement-learning
- grpo
- combinatorial-optimization
- code-generation
- sds
- icml-2026
datasets:
- SoheylM/OpenR1-SDS-10k-seed303
library_name: transformers
---

# Qwen2.5-Coder-14B-Instruct-GRPO-SDS-Ablation-Diversity-seed303

## Description
Diversity ablation (seed 303).

This model is part of the **Neural Solver Synthesis** project (ICML 2026).
It acts as a compiled solver for the SDS problem.

## Artifacts
- **Training Data**: [SoheylM/OpenR1-SDS-10k-seed303](https://huggingface.co/datasets/SoheylM/OpenR1-SDS-10k-seed303)
- **Base Model**: Qwen 2.5 Coder 14B