Changes to handler

handler.py

@@ -3,8 +3,8 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 
 MODEL_NAME = "kasterkeqi/Lumo-8B-Fork-Sol-Copilot"
 
-class ModelHandler:
-    def __init__(self):
+class EndpointHandler:
+    def __init__(self, model_dir=None):
         """Initialize the model and tokenizer."""
         self.device = "cuda" if torch.cuda.is_available() else "cpu"
         print(f"Loading model on {self.device}...")
@@ -32,4 +32,4 @@ class ModelHandler:
 
         # Decode output
         response = self.tokenizer.decode(output_tokens[0], skip_special_tokens=True)
-        return {"response": response}
+        return {"response": response}