---
license: apache-2.0
datasets:
- Montecarlo2024/Python_Reason_D_Qwen_3_40k
base_model:
- HuggingFaceTB/SmolLM3-3B
---
This is a test of SmolLM3-3B trained from Qwen3-4B 2507 distilled 30k dataset, attempting to Python reason smaller models.