Update README.md

README.md

@@ -70,18 +70,20 @@ You can also run this model using the following code:
 import transformers
 from transformers import AutoTokenizer
 
+model_id = "halbihn/NeuralHermes-2.5-Mistral-7B"
+
 # Format prompt
 message = [
     {"role": "system", "content": "You are a helpful assistant chatbot."},
     {"role": "user", "content": "What is a Large Language Model?"}
 ]
-tokenizer = AutoTokenizer.from_pretrained(new_model)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
 prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False)
 
 # Create pipeline
 pipeline = transformers.pipeline(
     "text-generation",
-    model=new_model,
+    model=model_id,
     tokenizer=tokenizer
 )
 
@@ -94,7 +96,8 @@ sequences = pipeline(
     num_return_sequences=1,
     max_length=200,
 )
-print(sequences[0]['generated_text'])
+response = sequences[0]['generated_text'].split("<|im_start|>assistant")[-1].strip()
+print(response)
 
 
 # streaming example