Update src/model_load.py

src/model_load.py

@@ -14,7 +14,7 @@ def load_model():
     tokenizer = AutoTokenizer.from_pretrained(model_name)
     model = AutoModelForCausalLM.from_pretrained(model_name,
                                                  device_map="auto",
-                                                 quantization_config=BitsAndBytesConfig(load_in_8bit=True),
+                                                 quantization_config=BitsAndBytesConfig(load_in_4bit=True),
                                                  max_memory=max_memory)
     
     # Crear pipeline de generación de texto