Update README.md

README.md

@@ -43,6 +43,7 @@ Below shows a code example on how to use this model in default(bf16) format
 
 ```python
 from transformers import AutoModel, AutoTokenizer
+
 model_slug = "pankajmathur/orca_mini_v8_0_70b"
 model = AutoModel.from_pretrained(model_slug)
 tokenizer = AutoTokenizer.from_pretrained(model_slug)
@@ -54,14 +55,16 @@ gen_input = tokenizer.apply_chat_template(messages, return_tensors="pt")
 model.generate(**gen_input)
 ```
 
-Below shows a code example on how to use this model in 4-bit format via bitsandbytes library
+Below shows a code example on how to use this model in 8-bit format via bitsandbytes library
 
 ```python
-from transformers import AutoModel, AutoTokenizer, BitsAndBytesConfig
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+
 model_slug = "pankajmathur/orca_mini_v8_0_70b"
-quantization_config = BitsAndBytesConfig(load_in_4bit=True)
+quantization_config = BitsAndBytesConfig(load_in_8bit=True)
 quantized_model = AutoModelForCausalLM.from_pretrained(
-	model_slug, device_map="auto", torch_dtype=torch.bfloat16, quantization_config=quantization_config)
+    model_slug, device_map="auto", torch_dtype=torch.bfloat16, quantization_config=quantization_config)
 tokenizer = AutoTokenizer.from_pretrained(model_slug)
 messages = [
     {"role": "system", "content": "You are Orca Mini, a helpful AI assistant."},