added handler.py

handler.py

@@ -0,0 +1,23 @@
+from typing import Dict, List, Any
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+
+class PhiHandler():
+    def __init__(self, path=""):
+        self.model = AutoModelForCausalLM.from_pretrained(path, device_map="cuda", torch_dtype="auto", trust_remote_code=True)
+        self.tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct")
+        self.pipe = pipeline("text-generation", model=self.model, tokenizer=self.tokenizer)
+    def __call__(self, data:Dict[str, Any]) :
+        messages = data.pop("messages", None)
+        generation_args = data.pop("generation_args", None)
+
+        if generation_args==None :
+            generation_args = {
+                "max_new_tokens": 500,
+                "return_full_text": False,
+                "temperature": 0.0,
+                "do_sample": False,
+            }
+
+        output = self.pipe(messages, **generation_args)
+        return output[0]['generated_text']