metadata
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 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:
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}")