Update README.md

README.md

@@ -18,6 +18,7 @@ model,tokenizer=load_model(model_name = XLoRa_model_name,
                            use_flash_attention_2=True, 
                            dtype=torch.bfloat16,
                             )
+eos_token_id= tokenizer('<end_of_turn>', add_special_tokens=False, ) ['input_ids'][0]
 ```
 
 ```
@@ -60,9 +61,7 @@ Then, use as follows:
 ```
 from IPython.display import display, Markdown
 q='''What is graphene?'''
-res=generate_XLoRA_Gemma( system_prompt='You design materials.', 
-         prompt=q, max_new_tokens=1024, temperature=0.3,  )
-
+res=generate_XLoRA_Gemma( system_prompt='You design materials.', prompt=q, max_new_tokens=1024, temperature=0.3, eos_token=eos_token_id)
 display (Markdown(res))
 ```
 ## Model Details