Update README.md

README.md

@@ -45,6 +45,7 @@ pipeline_tag: text-generation
 ```python
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+
 tokenizer = AutoTokenizer.from_pretrained("upstage/Llama-2-70b-instruct-v2")
 model = AutoModelForCausalLM.from_pretrained(
     "upstage/Llama-2-70b-instruct-v2",
@@ -53,10 +54,12 @@ model = AutoModelForCausalLM.from_pretrained(
     load_in_8bit=True,
     rope_scaling={"type": "dynamic", "factor": 2} # allows handling of longer inputs
 )
+
 prompt = "### User:\nThomas is very healthy, but he has to go to the hospital every day. What could be the reasons?\n\n### Assistant:\n"
 inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 del inputs["token_type_ids"]
 streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+
 output = model.generate(**inputs, streamer=streamer, use_cache=True, max_new_tokens=float('inf'))
 output_text = tokenizer.decode(output[0], skip_special_tokens=True)
 ```