Update README.md

README.md

@@ -18,8 +18,8 @@ pipeline_tag: text-classification
 
 [Pleias](https://huggingface.co/PleIAs)
 
-DeBERTa-v3-small model
-trained on 600k samples from Toxic Commons
+
+Celadon is a DeBERTa-v3-small finetune with five classification heads, trained on 600k samples from Toxic Commons.
 
 This classifier is primarily aimed at historical cultural heritage data, like that in [Common Corpus]
 
@@ -32,11 +32,33 @@ Five types of toxicity classification:
 
 
 Read more about the training details in the paper, [Toxicity of the Commons: Curating Open-Source Pre-Training Data] by [Catherine Arnett](https://huggingface.co/catherinearnett), [Eliot Jones](https://huggingface.co/eliotj), Ivan P. Yamshchikov, [Pierre-Carl Langlais](https://huggingface.co/Pclanglais). 
-Code for generating the annotations and training the model is available on [GitHub](https://github.com/eliotjones1/celadon)
+For more detailed code regarding generating the annotations in Toxic Commons, training the model, and using the model, please refer to the official [GitHub](https://github.com/eliotjones1/celadon) repository. 
 
 
 # How to Use
 
+```
+from transformers import AutoTokenizer
+from model import MultiHeadDebertaForSequenceClassification
+
+tokenizer = AutoTokenizer.from_pretrained("PleIAs/celadon")
+model = MultiHeadDebertaForSequenceClassification.from_pretrained("PleIAs/celadon")
+model.eval()
+
+sample_text = "This is an example of a normal sentence"
+
+inputs = tokenizer(sample_text, return_tensors="pt", padding=True, truncation=True)
+outputs = model(**inputs)
+
+categories = ['Race/Origin', 'Gender/Sex', 'Religion', 'Ability', 'Violence']
+predictions = outputs.argmax(dim=-1).squeeze().tolist()[0]  
+
+# Print the classification results for each category
+print(f"Text: {sample_text}")
+for i, category in enumerate(categories):
+    print(f"Prediction for Category {category}: {predictions[i]}")
+```
+
 # How to Cite
 
 ```