Update app.py

app.py

@@ -3,25 +3,10 @@ import json
 import spaces
 import gradio as gr
 import torch
-from distilabel.llms import TransformersLLM
-from distilabel.steps.tasks.argillalabeller import ArgillaLabeller
-from transformers import BitsAndBytesConfig
-
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_compute_dtype=torch.bfloat16,
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_quant_type="nf4",
-)
-
+from distilabel.llms import vLLM
 
-llm = TransformersLLM(
-    model="microsoft/Phi-3-mini-4k-instruct",
-    torch_dtype="float16",
-    model_kwargs={
-        "quantization_config": quantization_config,
-        "device_map": "auto",
-    },
+llm = vLLM(
+    model="Qwen/Qwen2-0.5B-Instruct-GGUF"
 )
 task = ArgillaLabeller(llm=llm)
 task.load()