Update README.md

README.md

@@ -10,12 +10,10 @@ pip install --upgrade accelerate fbgemm-gpu torch
 ```
 
 ```python
-from transformers import FbgemmFp8Config, AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-model_name = "MLP-KTLim/llama-3-Korean-Bllossom-8B"
-quantization_config = FbgemmFp8Config()
-model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", quantization_config=quantization_config)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained("PerRing/llama-3-Korean-Bllossom-8B-fp8")
+model = AutoModelForCausalLM.from_pretrained("PerRing/llama-3-Korean-Bllossom-8B-fp8",device_map='auto')
 ```
 
 ```python