Update README.md

README.md

@@ -52,6 +52,10 @@ model = LLaMAForCausalLM.from_pretrained(
     "cosimoiaia/Loquace-70m",
     load_in_8bit=True,
     device_map="auto",
+    quantization_config=BitsAndBytesConfig(
+      load_in_4bit=True,
+      llm_int8_has_fp16_weight=False
+    )
 )
 ```