Update README.md

README.md

@@ -29,3 +29,23 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 tokenizer = AutoTokenizer.from_pretrained("asif00/bangla-llama-4bit")
 model = AutoModelForCausalLM.from_pretrained("asif00/bangla-llama-4bit")
 ```
+
+
+# To get a cleaned up version of the response, you can use:
+
+```python
+def generate_response(question, context):
+    inputs = tokenizer([
+        prompt.format(
+            question,
+            context, 
+            ""
+        )
+    ], return_tensors="pt").to("cuda")
+
+    outputs = model.generate(**inputs, max_new_tokens=1024, use_cache=True)
+    responses = tokenizer.batch_decode(outputs, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+    response_start = responses.find("### Response:") + len("### Response:")
+    response = responses[response_start:].strip()
+    return response
+```