Update app.py

app.py

@@ -8,25 +8,35 @@ app = FastAPI()
 MODEL_REPO = "microsoft/Phi-3-mini-4k-instruct-gguf"
 MODEL_FILE = "Phi-3-mini-4k-instruct-q4.gguf"
 
+print("Downloading model...")
+
 model_path = hf_hub_download(
     repo_id=MODEL_REPO,
     filename=MODEL_FILE
 )
 
+print("Loading model...")
+
 llm = Llama(
     model_path=model_path,
     n_ctx=2048,
     n_threads=2
 )
 
+print("Model loaded successfully!")
+
 class Prompt(BaseModel):
     prompt: str
 
-@app.post("/generate")
-def generate(req: Prompt):
-    output = llm(req.prompt, max_tokens=200)
-    return {"response": output["choices"][0]["text"]}
-
 @app.get("/")
 def root():
-    return {"status": "AI running"}
+    return {"status": "AI Engine Running 🚀"}
+
+@app.post("/generate")
+def generate(data: Prompt):
+    output = llm(
+        data.prompt,
+        max_tokens=200,
+        stop=["</s>"]
+    )
+    return {"response": output["choices"][0]["text"]}