Upload README.md with huggingface_hub

README.md

@@ -16,24 +16,33 @@ pipeline_tag: feature-extraction
 This model is the foundational scoring backend for the [BioTarget](https://github.com/homerquan/biotarget) end-to-end drug discovery pipeline.
 
 ## 🎯 Model Architecture
-- **Graph Encoder**: [SchNet](https://github.com/atomistic-machine-learning/schnetpack) (3D Message Passing Neural Network). Processes atomic coordinates  and atomic numbers .
-- **Text Encoder**: 
+- **Graph Encoder**: [SchNet](https://github.com/atomistic-machine-learning/schnetpack) (3D Message Passing Neural Network). Processes atomic coordinates `pos` and atomic numbers `z`.
+- **Text Encoder**: `distilbert-base-uncased`
 - **Latent Dimension**: 128
 - **Objective**: InfoNCE (Contrastive Loss)
 
 ## 💻 Usage
 
-To use this checkpoint, you will need the usage: drugclip [-h] {data,train,infer} ...
+To use this checkpoint, you will need the `drugclip` python package.
 
-drugclip - Multimodal Graph-Text Drug Design CLI
+```python
+import torch
+from drugclip.models.align_model import DrugCLIP
 
-positional arguments:
-  {data,train,infer}
+# 1. Initialize the architecture
+model = DrugCLIP(hidden_channels=64, out_dim=128, text_model='distilbert-base-uncased')
 
-options:
-  -h, --help          show this help message and exit python package.
+# 2. Load the downloaded checkpoint
+state_dict = torch.load('best.ckpt', map_location='cpu')
+model.load_state_dict(state_dict)
+model.eval()
 
+# 3. Embed natural language clinical intent
+text_emb = model.text_encoder(['This molecule failed clinical trials due to severe toxicity and side effects.'])
+text_emb = torch.nn.functional.normalize(text_emb, p=2, dim=1)
 
+# (Molecular processing requires RDKit and PyTorch Geometric Data Batches)
+```
 
 ## 📚 Training Data
 The model's contrastive space was constructed using: