README.md

---
base_model: openGPT-X/Teuken-7B-instruct-research-v0.4
license: mit
---
# Teuken7B  QLoRA – Grounding Act Classification

This model is a fine-tuned version of [openGPT-X/Teuken-7B-instruct-research-v0.4](https://huggingface.co/openGPT-X/Teuken-7B-instruct-research-v0.4) optimized using QLoRA for efficient binary classification of German dialogue utterances into:

- **advance**: Contribution that moves the dialogue forward (e.g. confirmations, follow-ups, elaborations)
- **non_advance**: Other utterances (e.g. vague responses, misunderstandings, irrelevant comments)

---

## Use Cases

- Dialogue system analysis
- Teacher-student interaction classification
- Grounding in institutional advising or classroom discourse

---
 
## How to Use:

```python
from transformers import AutoModelForSequenceClassification, AutoTokenizer
import torch
tokenizer = AutoTokenizer.from_pretrained("openGPT-X/Teuken-7B-instruct-research-v0.4")

model = AutoModelForSequenceClassification.from_pretrained("MB55/teuken7b-advance-classifier")
model.eval()

def predict(text):
    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
    if "token_type_ids" in inputs:
        del inputs["token_type_ids"]
    with torch.no_grad():
        outputs = model(**inputs)
    logits = outputs.logits
    predicted_class = logits.argmax(dim=-1).item()
    return predicted_class

text = "Ich bin da."
prediction = predict(text)

print(f"Predicted class: {prediction}")