Update README.md

README.md

@@ -12,6 +12,35 @@ tags:
 - 'Question_Answers'
 ---
 
-# ZenGQ
+# ZenGQ - BERT for Question Answering
 
-A question-answering model trained on the `Rep00Zon` dataset.
+This is a fine-tuned BERT model for question answering tasks, trained on a custom dataset.
+
+## Model Details
+
+- **Model:** BERT-base-uncased
+- **Task:** Question Answering
+- **Dataset:** Custom dataset
+
+## Usage
+
+### Load the model
+
+```python
+from transformers import AutoTokenizer, AutoModelForQuestionAnswering, pipeline
+
+tokenizer = AutoTokenizer.from_pretrained("prabinpanta0/ZenGQ")
+model = AutoModelForQuestionAnswering.from_pretrained("prabinpanta0/ZenGQ")
+
+qa_pipeline = pipeline("question-answering", model=model, tokenizer=tokenizer)
+
+context = "Berlin is the capital of Germany."
+question = "What is the capital of Germany?"
+
+result = qa_pipeline(question=question, context=context)
+print(f"Answer: {result['answer']}")
+```
+
+### Training Details
+- Epochs: 3
+- Training Loss: 2.050335, 1.345047, 1.204442