Update app.py

app.py

@@ -2,15 +2,6 @@ from huggingface_hub import InferenceClient
 client = InferenceClient(
     "ecastera/eva-mistral-catmacaroni-7b-spanish"
 )
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    load_in_8bit=False,
-    llm_int8_threshold=6.0,
-    llm_int8_has_fp16_weight=False,
-    bnb_4bit_compute_dtype="float16",
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_quant_type="nf4")
-
 generate_kwargs = dict(
         temperature=0.1,
         max_new_tokens=256,