Disable 4-bit quantization for the model

app.py

@@ -3,7 +3,12 @@ from pydantic import BaseModel
 from transformers import pipeline
 
 # Load your Hugging Face model
-model = pipeline("text-generation", model="devops-bda/Abap")
+# model = pipeline("text-generation", model="devops-bda/Abap")
+model = pipeline(
+    "text-generation",
+    model="devops-bda/Abap",
+    model_kwargs={"load_in_4bit": False}  # Disable 4-bit quantization
+)
 
 # Initialize FastAPI app
 app = FastAPI()