|
|
--- |
|
|
license: mit |
|
|
base_model: |
|
|
- utter-project/EuroLLM-9B-Instruct |
|
|
--- |
|
|
|
|
|
# EuroLLM QLoRA – Grounding Act Classification |
|
|
|
|
|
This model is a fine-tuned version of [EuroLLM-9B-Instruct](https://huggingface.co/utter-project/EuroLLM-9B-Instruct) 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 AutoTokenizer, AutoModelForSequenceClassification |
|
|
from peft import PeftModel, PeftConfig |
|
|
|
|
|
peft_config = PeftConfig.from_pretrained("MB55/EuroLLM-Classifier-QLoRA") |
|
|
base_model = AutoModelForSequenceClassification.from_pretrained(peft_config.base_model_name_or_path) |
|
|
model = PeftModel.from_pretrained(base_model, "MB55/EuroLLM-Classifier-QLoRA") |
|
|
tokenizer = AutoTokenizer.from_pretrained("MB55/EuroLLM-Classifier-QLoRA") |
