Update README.md

README.md

@@ -4,17 +4,20 @@ base_model:
 - deepset/gbert-large
 ---
 
-# MB55/gbert-lora-final
+# Gbert QLoRA – Grounding Act Classification
 
-This model is a LoRA-fine-tuned version of [deepset/gbert-large](https://huggingface.co/deepset/gbert-large) for binary classification tasks in German. It uses QLoRA for memory-efficient training on CPU or GPU.
+This model is a fine-tuned version of [deepset/gbert-large](https://huggingface.co/deepset/gbert-large), 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
 
-## Model Details
 
-- **Base model**: `deepset/gbert-large`
-- **LoRA fine-tuning**: Performed with QLoRA
-- **Task**: Binary classification (e.g., ADVANCE vs NON-ADVANCE)
-- **Language**: German
-- **Framework**: PyTorch (via Hugging Face Transformers + PEFT)
 
 ## How to Use