Update main.py

main.py

@@ -18,7 +18,7 @@ class validation(BaseModel):
 app = FastAPI()
 
 #Zephyr completion
-@app.post("/llama_on_cpu")
+@app.post("/")
 async def stream(item: validation):
     system_prompt = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.'
     prompt =  f"<s>[INST]<<SYS>>\n + {system_prompt} + <</SYS>>\n{item.prompt.strip()}[/INST]"