added the handler

handler.py

@@ -0,0 +1,16 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+class EndpointHandler:
+    def __init__(self, path=""):
+        self.tokenizer = AutoTokenizer.from_pretrained(path)
+        self.model = AutoModelForCausalLM.from_pretrained(path, torch_dtype=torch.float16)
+        self.model.eval()
+
+    def __call__(self, inputs):
+        prompt = inputs.get("inputs", "")
+        inputs = self.tokenizer(prompt, return_tensors="pt").to(self.model.device)
+        with torch.no_grad():
+            outputs = self.model.generate(**inputs, max_new_tokens=200)
+        response = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
+        return {"generated_text": response}