add classification example

README.md

@@ -76,10 +76,24 @@ Clinical Mosaic was pre-trained on deidentified clinical notes from MIMIC-IV-NOT
 Install the Hugging Face Transformers library and load the model as follows:
 
 ```python
-from transformers import AutoTokenizer, AutoModel
+from transformers import AutoTokenizer, AutoModel, AutoModelForSequenceClassification, BertTokenizer, BertConfig
+import torch
 
-tokenizer = AutoTokenizer.from_pretrained("path/to/clinical-mosaic")
-model = AutoModel.from_pretrained("path/to/clinical-mosaic")
+tokenizer = BertTokenizer.from_pretrained('bert-base-uncased') # MosaicBERT uses the standard BERT tokenizer
+config = BertConfig.from_pretrained('Sifal/ClinicalMosaic') # the config needs to be passed in
+
+# Set the hidden size and number of labels:
+config.num_labels = 4
+config.hidden_size = 768
+
+ClassifierClincalMosaic = AutoModelForSequenceClassification.from_pretrained('Sifal/ClinicalMosaic', config=config, trust_remote_code=True)
+
+# Example usage
+
+clinical_text = "..."
+
+inputs = tokenizer(clinical_text, return_tensors="pt")
+embeddings = ClassifierClincalMosaic(**inputs)
 ```
 
 Further instructions and example scripts are provided in the model’s repository.