Update README.md

README.md

@@ -13,4 +13,49 @@ tags:
 - zero-shot
 - mmBERT
 - text-classification
----
+---
+BlameBERT is the first model for zero-shot classification of blame in Danish (following the definition of [Bilotta et al.](http://arxiv.org/abs/2504.06550)). As it is mmBERT based, it should theoretically generalize across languages, but it has only been tested in Danish.
+
+BlameBERT has been tested against [QWEN 3.5:9B](https://ollama.com/library/qwen3.5:9b) in a schema-constrained setting, outperforming it on the test set.
+
+More details can be found in the GitHub for the [BlameBERT Project](https://github.com/Lundsfryd/BlameBERT).
+
+The model is ready for use straight out of the box.
+
+**Example usage**
+```
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+import numpy as np
+
+tokenizer = AutoTokenizer.from_pretrained("Lundsfryd/DaBERT-BlameDetector")
+model = AutoModelForMaskedLM.from_pretrained("Lundsfryd/DaBERT-BlameDetector")
+
+def predict(text):
+  inputs = tokenizer(
+      text,
+      padding=True,
+      truncation=True,
+      max_length=512, #mmBERT accepts up to 8,192 tokens. For our purposes input was capped at 512.
+      return_tensors='pt'
+  )
+  
+  inputs = {k: v.to(model.device) for k, v in inputs.items()}
+  
+  with torch.no_grad():
+      outputs = model(**inputs)
+      logits = outputs.logits
+      probabilities = torch.softmax(logits, dim=1)
+      predicted_class = torch.argmax(probabilities, dim=1).item()
+      confidence = probabilities[0][predicted_class].item()
+  
+  return predicted_class, confidence, probabilities[0].cpu().numpy()
+
+texts = [
+  "Jeg er opmærksom på fængselspersonalets vilkår.",
+  "Det kommer både de studerende og erhvervslivet til gode.",
+  "Jeg er enig i, at der er kommet for mange hertil, som ikke vil Danmark, som ikke opfører sig ordentligt, som begår kriminalitet, og som i øvrigt med deres ideologiske tilgang til både religion og politik er med til at undergrave vores demokrati."
+]
+
+
+```