Add pipeline tag and improve metadata

README.md

@@ -1,26 +1,29 @@
 ---
-license: mit
 library_name: pytorch
+license: mit
+pipeline_tag: text-generation
 tags:
-  - gdds
-  - discrete-diffusion
-  - language-modeling
-  - research
-  - pytorch
+- gdds
+- discrete-diffusion
+- language-modeling
+- research
+- pytorch
 ---
 
 # GDDS Checkpoints
 
 Official checkpoint bundle for the paper **Generalized Discrete Diffusion from Snapshots**.
 
+Generalized Discrete Diffusion from Snapshots (GDDS) is a unified framework for discrete diffusion modeling that supports arbitrary noising processes over large discrete state spaces. It introduces a training objective based on snapshot latents rather than the entire noising path, allowing for efficient training and high-quality generation.
+
 ## Model Sources
 
-- Paper: https://huggingface.co/papers/2603.21342
-- arXiv: https://arxiv.org/abs/2603.21342
-- Code: https://github.com/ozekri/gdds
-- Project page: https://oussamazekri.fr/gdds
+- **Paper:** [Generalized Discrete Diffusion from Snapshots](https://huggingface.co/papers/2603.21342)
+- **arXiv:** [2603.21342](https://arxiv.org/abs/2603.21342)
+- **Code:** [GitHub - ozekri/gdds](https://github.com/ozekri/gdds)
+- **Project Page:** [https://oussamazekri.fr/gdds](https://oussamazekri.fr/gdds)
 
-## Included checkpoints
+## Included Checkpoints
 
 | File | Method | Notes |
 | --- | --- | --- |
@@ -35,8 +38,7 @@ Official checkpoint bundle for the paper **Generalized Discrete Diffusion from S
 
 ## Usage
 
-These files are PyTorch Lightning checkpoints intended to be used with the
-`gdds` codebase.
+These files are PyTorch Lightning checkpoints intended to be used with the [`gdds`](https://github.com/ozekri/gdds) codebase.
 
 ```bash
 git clone https://github.com/ozekri/gdds.git
@@ -44,6 +46,7 @@ cd gdds
 pip install -r requirements.txt
 pip install -e .
 
+# Example evaluation using a checkpoint
 PYTHONPATH=src python -m discrete_diffusion.evaluations.ppl_eval \
   data=openwebtext \
   model=small \
@@ -51,8 +54,7 @@ PYTHONPATH=src python -m discrete_diffusion.evaluations.ppl_eval \
   eval.checkpoint_path=/path/to/checkpoints/mdlm_500k.ckpt
 ```
 
-For sampling and other evaluations, use the same repository and pass the
-relevant checkpoint path through the evaluation config.
+For sampling and other evaluations, use the same repository and pass the relevant checkpoint path through the Hydra evaluation config.
 
 ## Citation
 
@@ -66,4 +68,4 @@ relevant checkpoint path through the evaluation config.
   primaryClass={stat.ML},
   url={https://arxiv.org/abs/2603.21342},
 }
-```
+```