Switch model from llama to a small 1.5B Qwen

app.py

@@ -4,7 +4,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 import plotly.express as px
 
 
-model_name = 'meta-llama/Llama-2-7b-hf'
+model_name = 'Qwen/Qwen2-1.5B'
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
 
 @st.cache_resource