Update README.md

README.md

@@ -54,7 +54,7 @@ The model was converted using [this notebook](https://nbviewer.org/urls/huggingf
 ### How to use
 
 ```sh
-wget https://huggingface.co/mrm8488/bertin-gpt-j-6B-ES-8bit/resolve/main/utils.py -O utils.py
+wget https://huggingface.co/mrm8488/bertin-gpt-j-6B-ES-8bit/resolve/main/utils.py -O Utils.py
 pip install transformers
 pip install bitsandbytes-cuda111==0.26.0
 ```
@@ -63,28 +63,7 @@ pip install bitsandbytes-cuda111==0.26.0
 import transformers
 import torch
 
-from utils import convert_to_int8
-
-
-class GPTJBlock(transformers.models.gptj.modeling_gptj.GPTJBlock):
-    def __init__(self, config):
-        super().__init__(config)
-
-        convert_to_int8(self.attn)
-        convert_to_int8(self.mlp)
-
-
-class GPTJModel(transformers.models.gptj.modeling_gptj.GPTJModel):
-    def __init__(self, config):
-        super().__init__(config)
-        convert_to_int8(self)
-        
-
-class GPTJForCausalLM(transformers.models.gptj.modeling_gptj.GPTJForCausalLM):
-    def __init__(self, config):
-        super().__init__(config)
-        convert_to_int8(self)
-
+from Utils import GPTJBlock, GPTJForCausalLM
 
 device = 'cuda' if torch.cuda.is_available() else 'cpu'