Update main.py

main.py

@@ -1,4 +1,4 @@
-from ctransformers import AutoModelForCausalLM, AutoTokenizer
+from llama_cpp import Llama
 from fastapi import FastAPI, Form, HTTPException
 from pydantic import BaseModel
 import torch
@@ -8,8 +8,7 @@ app = FastAPI()
 
 # Load the model and tokenizer
 model_name = "model.gguf"  # Replace with your model name
-test_model = AutoModelForCausalLM.from_pretrained(model_name)
-test_tokenizer = AutoTokenizer.from_pretrained(model_name)
+test_model = Llama(model_name)
 
 class RequestBody(BaseModel):
     prompt: str
@@ -42,4 +41,4 @@ async def generate_text(request: RequestBody):
 
 @app.get("/")
 async def read_root():
-    return {"message": "Welcome to the LLM FastAPI application!"}
+    return {"message": "Welcome to the RetroLLM app!"}