update handler.py

handler.py

@@ -1,24 +1,20 @@
 from typing import Dict, List, Any
 from transformers import AutoTokenizer, AutoModelForCausalLM
-from accelerate import Accelerator
 
-
-
-class EndpointHandler():
+class EndpointHandler:
     def __init__(self, path=""):
-      model_id = "DisgustingOzil/Academic-MCQ-Generator"
-      load_in_4bit = True
-      max_seq_length = 2048
-      tokenizer = AutoTokenizer.from_pretrained(model_id)
-      model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=load_in_4bit)
-
+        model_id = "DisgustingOzil/Academic-MCQ-Generator"
+        load_in_4bit = True
+        self.tokenizer = AutoTokenizer.from_pretrained(model_id)
+        self.model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=load_in_4bit)
+    
     def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
-        input_text = data.pop("input_text",data)
+        input_text = data.pop("input_text", data)
         inputs = self.tokenizer(input_text, return_tensors="pt")
         outputs = self.model.generate(
-              **inputs,
-              max_length=1000,
-              num_return_sequences=1,
-                )
+            **inputs,
+            max_length=1000,
+            num_return_sequences=1,
+        )
         output_text = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
-        return output_text
+        return [{"generated_text": output_text}]