Update README.md

README.md

@@ -16,6 +16,7 @@ The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned
 ## Instruction format
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
 device = "cuda" # the device to load the model onto
 
@@ -30,10 +31,12 @@ model = AutoModelForCausalLM.from_pretrained(model_name,
                                              torch_dtype=torch.bfloat16,
                                             )
                                             
+tokenizer = AutoTokenizer.from_pretrained(base_model_id,add_bos_token=True,trust_remote_code=True)
+
 model.config.use_cache = True
 def stream(user_prompt):
     runtimeFlag = "cuda:0"
-    system_prompt = 'The following is an excerpt from MODULAR_MOJO from the section on roadmap.'
+    system_prompt = 'MODULAR_MOJO'
     B_INST, E_INST = "[INST]", "[/INST]"
     prompt = f"{system_prompt}{B_INST}{user_prompt.strip()}\n{E_INST}"
     inputs = tokenizer([prompt], return_tensors="pt").to(runtimeFlag)