Create handler.py

handler.py

@@ -0,0 +1,29 @@
+from typing import Any, Dict, List
+
+import torch
+from transformers import AutoTokenizer, Qwen2ForCausalLM, pipeline
+
+dtype = torch.bfloat16 if torch.cuda.get_device_capability()[0] == 8 else torch.float16
+
+
+class EndpointHandler:
+    def __init__(self, path=""):
+        # load the model
+        self.tokenizer = AutoTokenizer.from_pretrained(path)
+        model = Qwen2ForCausalLM.from_pretrained(
+            path, device_map="auto", torch_dtype=dtype
+        )
+        # create inference pipeline
+        self.pipeline = pipeline("text-generation", model=model, tokenizer=self.tokenizer)
+
+    def __call__(self, data: Any) -> List[List[Dict[str, float]]]:
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", None)
+
+        # pass inputs with all kwargs in data
+        if parameters is not None:
+            prediction = self.pipeline(inputs, tokenizer=self.tokenizer, **parameters)
+        else:
+            prediction = self.pipeline(inputs)
+        # postprocess the prediction
+        return prediction