Update app.py

app.py

@@ -4,10 +4,7 @@ from pydantic import BaseModel
 from huggingface_hub import InferenceClient
 
 app = FastAPI()
-client = InferenceClient(
-    provider="hf-inference",
-    api_key=os.environ.get("HF_TOKEN")
-)
+client = InferenceClient(api_key=os.environ.get("HF_TOKEN"))
 
 class Request(BaseModel):
     prompt: str
@@ -19,9 +16,9 @@ def home():
 @app.post("/generate")
 def generate_text(request: Request):
     messages = [{"role": "user", "content": request.prompt}]
-    completion = client.chat.completions.create(
-        model="Qwen/Qwen2.5-72B-Instruct",
+    response = client.chat_completion(
         messages=messages,
+        model="HuggingFaceTB/SmolLM2-1.7B-Instruct",
         max_tokens=500
     )
-    return {"response": completion.choices[0].message.content}
+    return {"response": response.choices[0].message.content}