Add model card

This PR ensures:
- the model is linked to (and shows up at) https://huggingface.co/papers/2508.05629
- has the relevant `library_name` and `pipeline_tag`.

More best practices here: https://huggingface.co/docs/hub/model-release-checklist#writing-a-comprehensive-model-card

README.md

@@ -1,3 +1,9 @@
----
-license: mit
----
+---
+license: mit
+library_name: transformers
+pipeline_tag: text-generation
+---
+
+This model was presented in the paper [On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification](https://huggingface.co/papers/2508.05629).
+
+Code: https://github.com/yongliang-wu/DFT?tab=readme-ov-file