Update app.py

app.py

@@ -5,7 +5,7 @@ from typing import Iterator
 from mongoengine import connect, Document, StringField, SequenceField
 import gradio as gr
 import spaces
-from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextIteratorStreamer
 from peft import PeftModel
 
 # Constants
@@ -29,7 +29,7 @@ if not torch.cuda.is_available():
     DESCRIPTION += "\n<p>Running on CPU 🥶 This demo does not work on CPU.</p>"
 
 # Model and Tokenizer Configuration
-model_id = "meta-llama/Llama-2-7b-chat-hf"
+model_id = "meta-llama/Llama-2-7b-hf"
 bnb_config = BitsAndBytesConfig(
     load_in_4bit=True,
     bnb_4bit_use_double_quant=False,