model card

MODEL_CARD.md

@@ -0,0 +1,43 @@
+# 🧩 Model Card
+
+## **Model Details**
+- **Model name:**  Chemprop Message Passing Neural Network Tox21 Baseline
+- **Developer:**  
+- **Paper URL:**  https://pubs.acs.org/doi/full/10.1021/acs.jcim.3c01250
+- **Model type / architecture:**  Message Passing Neural Network implemented using Chemprop.
+- **Hyperparameters:**
+- **Inference:**  
+- **Model version:**  
+- **Model date:**  
+- **Reproducibility:** Code for full training is available and enables reproducible retraining of the model from scratch.
+
+A multitask network is trained for all Tox21 targets.
+
+---
+
+## **Intended Use**
+Access via FastAPI endpoint. Upon receiving a Tox21 prediction request,
+the model generates and returns predictions for all Tox21 targets simultaneously.
+
+---
+
+## **Metric**
+Each Tox21 task is evaluated using the area under the receiver operating characteristic curve
+(AUC). Overall performance is reported as the mean AUC across all individual tasks.
+
+---
+
+## **Training Data**
+Tox21 training and validation sets.
+
+---
+
+## **Evaluation Data**
+Tox21 test set.
+
+---
+
+## **Hugging Face Space Details**
+- **Space:**  link
+- **Git commit hash:**  link
+