Add README

README.md

@@ -1 +1,43 @@
-# GenRec: Memorization & Generalization Model Checkpoints
+# MemGen Checkpoints
+
+Checkpoints and artifacts for **On the Memorization and Generalization of Generative Recommendation**.
+
+[Paper] [Code] [Dataset]
+
+[Paper]: <link not ready yet>
+[Code]: https://github.com/Jamesding000/MemGen-GR
+[Dataset]: https://huggingface.co/datasets/jamesding0302/memgen-annotations
+
+## Folder Structure
+
+- `SASRec/`: SASRec checkpoints (`.pth`)
+- `TIGER/`: TIGER checkpoints (`.pth`)
+- `semantic_ids/`: semantic ID files (`.sem_ids`) used to train the corresponding TIGER checkpoints
+
+All checkpoints are trained with the **default configs** in the code repo. If you are unsure about model size / architecture, please refer to the configs in [Code].
+
+## Download (example)
+
+```python
+from huggingface_hub import hf_hub_download
+
+repo_id = "jamesding0302/memgen-checkpoints"
+
+ckpt_path = hf_hub_download(repo_id, "TIGER/TIGER-AmazonReviews2014-category_Sports_and_Outdoors.pth")
+sem_ids_path = hf_hub_download(
+    repo_id,
+    "semantic_ids/AmazonReviews2014-Sports_and_Outdoors_sentence-t5-base_256,256,256,256.sem_ids",
+)
+```
+
+## Evaluation
+```
+CUDA_VISIBLE_DEVICES=0 python mem_gen_evaluation.py \
+    --model=TIGER \
+    --dataset=AmazonReviews2014 \
+    --category=Sports_and_Outdoors \
+    --checkpoint_path=path/to/TIGER.pth \
+    --sem_ids_path=path/to/semantic_ids.sem_ids \
+    --eval=test \
+    --save_inference
+```