Update app.py

app.py

@@ -1,16 +1,13 @@
-from llama_cpp import Llama
+from fastapi import FastAPI
+from transformers import pipeline
 
-llm = Llama.from_pretrained(
-	repo_id="microsoft/Phi-3-mini-4k-instruct-gguf",
-	filename="Phi-3-mini-4k-instruct-fp16.gguf",
-)
+app = FastAPI()
 
-output = llm(
-	"Once upon a time,",
-	max_tokens=512,
-	echo=True
-)
-print(output)
+# Загрузка модели Hugging Face
+model = pipeline("text-generation", model="bartowski/Phi-3.5-mini-instruct-GGUF")
 
-if __name__ == '__app__':
-    app()
+@app.post("/predict")
+async def predict(text: str):
+    # Генерация ответа с помощью модели
+    result = model(text, max_length=50, num_return_sequences=1)
+    return {"response": result[0]["generated_text"]}