Create app.py

app.py

@@ -0,0 +1,24 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+app = FastAPI()
+
+# Load ChatDoctor model
+model_id = "z1111/ChatDoctor"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32
+)
+
+class ChatInput(BaseModel):
+    message: str
+
+@app.post("/chat")
+async def chat_handler(input: ChatInput):
+    inputs = tokenizer(input.message, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=200)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return {"response": response}