Update app.py

app.py

@@ -24,9 +24,9 @@ def configure_quantization():
 @st.cache_resource
 def initialize_llm(hf_token):
     # quantization_config = configure_quantization()
-    model_name = 'ericzzz/falcon-rw-1b-chat'
+    model_name = 'GeneZC/MiniChat-1.5-3B'
     return HuggingFaceLLM(
-        model_name = model_name, #meta-llama/Meta-Llama-3-8B-Instruct meta-llama/Llama-2-7b-chat-hf #google/gemma-7b-it #HuggingFaceH4/zephyr-7b-beta #'GeneZC/MiniChat-2-3B'
+        model_name = model_name, #meta-llama/Meta-Llama-3-8B-Instruct meta-llama/Llama-2-7b-chat-hf #google/gemma-7b-it #HuggingFaceH4/zephyr-7b-beta #'GeneZC/MiniChat-2-3B''ericzzz/falcon-rw-1b-chat'
         tokenizer_name = model_name,
         context_window=1900,
         # model_kwargs={"token": hf_token, "quantization_config": quantization_config},