xiaolesu's picture
Update README.md
14c72f0 verified
|
raw
history blame
627 Bytes
### xiaolesu/OsmosisProofling-SFT-NT-GRPO-NT-Overlap
Experimental checkpoint from "Data Overlap as a Post-Training Hyperparameter for Autoformalization." This is the **SFT+GRPO with 100% overlap** variant (Qwen3-8B, thinking disabled) -- the control condition where GRPO reuses SFT data entirely. See the [paper repo](https://github.com/suxls/data-overlap-autoformalization) for details, results, and all artifacts.
## 📄 Paper
This model is part of the experiments in:
**SFT-GRPO Data Overlap as a Post-Training Hyperparameter for Autoformalization**
Xiaole Su, Kasey Zhang, Andy Lyu
https://arxiv.org/abs/2604.13515