Update README.md

README.md

@@ -29,13 +29,14 @@ The model inherits the [GPT2LMHeadModel](https://huggingface.co/docs/transformer
 
 ### Password Generation
 
-Passwords can be sampled from the model using the [built-in generation methods](https://huggingface.co/docs/transformers/v4.30.0/en/main_classes/text_generation#transformers.GenerationMixin.generate) provided by HuggingFace and using the "start of password token" as seed (i.e. `<s>`). This code can be used to generate one password with PassGPT:
+Passwords can be sampled from the model using the [built-in generation methods](https://huggingface.co/docs/transformers/v4.30.0/en/main_classes/text_generation#transformers.GenerationMixin.generate) provided by HuggingFace and using the "start of password token" as seed (i.e. `<s>`). This code can be used to generate one password with PassGPT. Note you may need to generate an [access token](https://huggingface.co/docs/hub/security-tokens) to authenticate your download.
 
 ```
 from transformers import GPT2LMHeadModel
 from transformers import RobertaTokenizerFast
 
-tokenizer = RobertaTokenizerFast.from_pretrained("javirandor/passgpt-10characters", 
+tokenizer = RobertaTokenizerFast.from_pretrained("javirandor/passgpt-10characters",
+                                                  use_auth_token="YOUR_ACCESS_TOKEN",
                                                   max_len=12,
                                                   padding="max_length", 
                                                   truncation=True,
@@ -46,12 +47,12 @@ tokenizer = RobertaTokenizerFast.from_pretrained("javirandor/passgpt-10character
                                                   pad_token="<pad>",
                                                   truncation_side="right")
 
-model = GPT2LMHeadModel.from_pretrained("javirandor/passgpt-10characters").eval()
+model = GPT2LMHeadModel.from_pretrained("javirandor/passgpt-10characters", use_auth_token="YOUR_ACCESS_TOKEN").eval()
 
 NUM_GENERATIONS = 1
 
 # Generate passwords sampling from the beginning of password token
-g = model.generate(torch.tensor([[tokenizer.bos_token_id]]).cuda(),
+g = model.generate(torch.tensor([[tokenizer.bos_token_id]]),
                   do_sample=True,
                   num_return_sequences=NUM_GENERATIONS,
                   max_length=12,