Update README.md

README.md

@@ -1,5 +1,70 @@
----
-license: other
-license_name: link-attribution
-license_link: https://dejanmarketing.com/link-attribution/
----
+---
+license: other
+license_name: link-attribution
+license_link: https://dejanmarketing.com/link-attribution/
+language:
+- en
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+base_model: microsoft/deberta-v3-large
+pipeline_tag: text-classification
+tags:
+- grounding
+- retrieval
+- LLM-enhancement
+- DejanAI
+---
+
+[![Dejan AI Logo](https://dejan.ai/wp-content/uploads/2024/02/dejan.png)](https://dejan.ai/blog/grounding-classifier/)
+
+## Prompt Grounding Classifier — DeBERTa v3 Large (Fine-Tuned)
+
+This model predicts whether a natural language prompt **requires grounding** in external sources such as search, database, or retrieval-augmented generation (RAG).
+
+It was fine-tuned from [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) using a binary label format (`1 = requires grounding`, `0 = self-contained`).
+
+### Why this matters
+
+Routing decisions matter. This classifier acts as a gatekeeper for LLM pipelines by predicting whether a prompt should trigger external retrieval. It optimizes performance, reduces latency, and avoids unnecessary API calls.
+
+---
+
+## Model Details
+
+- 🧠 **Architecture**: DeBERTa v3 Large
+- ⚙️ **Training**: Full fine-tuning (no PEFT)
+- 🧪 **Batch size**: 24 (with accumulation)
+- 🔁 **Scheduler**: Cosine learning rate decay with warmup
+- 📉 **Dropout adjusted**: 0.1 for attention and hidden layers
+- 📦 **Final checkpoint size**: ~1.7 GB
+
+---
+
+## Example Predictions
+
+| Prompt                                               | Grounding | Confidence |
+|------------------------------------------------------|-----------|------------|
+| What’s the exchange rate for USD to Yen right now?   |     1     |   0.999    |
+| Tell me a bedtime story about a robot and a dragon.  |     0     |   0.996    |
+| Who is the current CEO of Microsoft?                 |     1     |   0.998    |
+
+---
+
+## How to Use
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch.nn.functional as F
+
+model = AutoModelForSequenceClassification.from_pretrained("dejan/deberta-grounding-classifier")
+tokenizer = AutoTokenizer.from_pretrained("dejan/deberta-grounding-classifier")
+
+prompt = "What time is the next train from Tokyo to Osaka?"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model(**inputs).logits
+probs = F.softmax(outputs, dim=-1)
+label = probs.argmax().item()
+confidence = probs[0][label].item()