Update app.py

app.py

@@ -74,7 +74,7 @@ def predict(message, history, system_prompt, temperature, max_new_tokens, top_k,
 # Load model
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,
+    load_in_4bit=False,
     bnb_4bit_compute_dtype=torch.bfloat16
 )
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
@@ -91,12 +91,9 @@ gr.ChatInterface(
     title=EMOJI + " " + MODEL_NAME,
     description=DESCRIPTION,
     examples=[
-        ["Can you solve the equation 2x + 3 = 11 for x?"],
-        ["Write an epic poem about Ancient Rome."],
-        ["Who was the first person to walk on the Moon?"],
-        ["Use a list comprehension to create a list of squares for numbers from 1 to 10."],
-        ["Recommend some popular science fiction books."],
-        ["Can you write a short story about a time-traveling detective?"]
+        ["Express joy and excitement about visiting a new place."],
+        ["I'm feeling really down today. Nothing seems to be going right."],
+        ["hey, How are you and what is your name?"],
     ],
     additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False),
     additional_inputs=[