Update app.py

app.py

@@ -10,7 +10,7 @@ access_token = os.getenv("Llama2")
 def greet(token, text):
 
  model = "meta-llama/Llama-2-7b-chat-hf"
- tokenizer = AutoTokenizer.from_pretrained(model, token=access_token)
+ tokenizer = AutoTokenizer.from_pretrained(model, token=access_token,use_safetensors=False)
  
  pipeline = transformers.pipeline(
  "text-generation",
@@ -23,15 +23,14 @@ def greet(token, text):
  do_sample=True,
  top_k=10,
  num_return_sequences=1,
- pad_token_id=tokenizer.eos_token_id,
+ eos_token_id=tokenizer.eos_token_id,
  token=access_token
  )
 
  llm = HuggingFacePipeline(pipeline = pipeline, model_kwargs = {'temperature':0})
 
  template = """
- Write a summary of the following text delimited by triple backticks.
- Return your response which covers the key points of the text.
+ Write a concise summary of the following text.
  ```{text}```
  SUMMARY:
  """