Update README.md

README.md

@@ -26,7 +26,6 @@ pipeline_tag: conversational
 
 ## Use in Transformers
 
-Please load the tokenizer with 'add_bos_token = True' parameter as the underlying OpenLLaMa model and this model were trained with a BOS token. 
 
 ```
 import os
@@ -36,7 +35,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 model_name = 'VMware/open-llama-0.3T-7B-open-instruct-v1.1'
 
 
-tokenizer = AutoTokenizer.from_pretrained(model_name, add_bos_token = True)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype= torch.float16, device_map = 'sequential')