Upload STGFORMER_TEST_E2E model trained on METR-LA

README.md

@@ -3,18 +3,18 @@ tags:
 - traffic-forecasting
 - time-series
 - graph-neural-network
-- stgformer_pretrained
+- stgformer_test_e2e
 datasets:
 - metr-la
 ---
 
-# Spatial-Temporal Graph Transformer (Pretrained) - METR-LA
+# Spatial-Temporal Graph Transformer (Test E2E) - METR-LA
 
-Spatial-Temporal Graph Transformer (Pretrained) (STGFORMER_PRETRAINED) trained on METR-LA dataset for traffic speed forecasting.
+Spatial-Temporal Graph Transformer (Test E2E) (STGFORMER_TEST_E2E) trained on METR-LA dataset for traffic speed forecasting.
 
 ## Model Description
 
-STGFormer pretrained checkpoint for METR-LA. This checkpoint contains pretrained model weights and imputation head from masked node pretraining. Use with load_from config option.
+STGFormer E2E test: pretrain->save->load->impute->train
 
 
 
@@ -28,7 +28,7 @@ STGFormer pretrained checkpoint for METR-LA. This checkpoint contains pretrained
 from utils.stgformer import load_from_hub
 
 # Load model from Hub
-model, scaler = load_from_hub("METR-LA", hf_repo_prefix="STGFORMER_PRETRAINED")
+model, scaler = load_from_hub("METR-LA", hf_repo_prefix="STGFORMER_TEST_E2E")
 
 # Get predictions
 from utils.stgformer import get_predictions
@@ -37,11 +37,11 @@ predictions = get_predictions(model, scaler, test_dataset)
 
 ## Training
 
-Model was trained using the STGFORMER_PRETRAINED implementation with default hyperparameters.
+Model was trained using the STGFORMER_TEST_E2E implementation with default hyperparameters.
 
 ## Citation
 
-If you use this model, please cite the original STGFORMER_PRETRAINED paper:
+If you use this model, please cite the original STGFORMER_TEST_E2E paper:
 
 ```bibtex
 @inproceedings{lan2022stgformer,

hub_metadata.json

@@ -1,6 +1,7 @@
 {
   "dataset": "METR-LA",
-  "checkpoint_type": "pretrained",
+  "metrics": {},
   "framework": "PyTorch",
-  "hf_repo_prefix": "STGFORMER_TEST_E2E"
+  "hf_repo_prefix": "STGFORMER_TEST_E2E",
+  "implementation": "internal"
 }

metadata.json

@@ -1,7 +1,7 @@
 {
   "dataset": "METR-LA",
-  "upload_date": "2025-12-08T14:20:40.447316",
+  "upload_date": "2025-12-08T14:24:03.974807",
   "metrics": {},
   "framework": "PyTorch",
-  "model_type": "STGFORMER_PRETRAINED"
+  "model_type": "STGFORMER_TEST_E2E"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:350a5689a70cc4efa505d08defefeb6afedef61247acad0d602fd0088982f40c
+oid sha256:1e53c220f7c2ff97a85951f4027bf8afa90ca47861ea1ba094ab41ed22fed344
 size 7231112

pretrained_checkpoint/metadata.json

@@ -1,6 +1,6 @@
 {
   "dataset": "METR-LA",
-  "upload_date": "2025-12-08T14:08:18.665977",
+  "upload_date": "2025-12-08T14:20:40.447316",
   "metrics": {},
   "framework": "PyTorch",
   "model_type": "STGFORMER_PRETRAINED"