Update README.md

README.md

@@ -9,4 +9,25 @@ metrics:
 base_model:
 - distilbert/distilbert-base-uncased
 pipeline_tag: text-classification
----
+---
+
+## Model Details
+Text classification model for ambiguity in questions. Classifies questions as ambiguous or clear. 
+Based on distilbert/distilbert-base-uncased.
+
+**Example:**
+
+"He gave it all he could." {'label': 'AMBIG', 'score': 0.7770335078239441}
+
+"Peter did his best for the football game." {'label': 'CLEAR': 0.7791128158569336}
+
+## Out-of-Scope Use
+The model was only trained to classify single questions. Other kinds of data are not tested.
+
+### Training Data
+I used a small part of the inquisitiveqg dataset mixed with a private dataset to train the model. A satisfactory model with 85.5% accuracy was created.
+
+#### Metrics
+"eval_accuracy": 0.8551401869158879,
+
+"eval_loss": 0.3658725619316101,