Update app.py

app.py

@@ -23,13 +23,14 @@ def configure_quantization():
 # Initialize the LLM
 @st.cache_resource
 def initialize_llm(hf_token):
-    quantization_config = configure_quantization()
+    # quantization_config = configure_quantization()
     model_name = 'HuggingFaceH4/zephyr-7b-beta'
     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
         tokenizer_name = model_name,
         context_window=3900,
-        model_kwargs={"token": hf_token, "quantization_config": quantization_config},
+        # model_kwargs={"token": hf_token, "quantization_config": quantization_config},
+        model_kwargs={"token": hf_token}
         tokenizer_kwargs={"token": hf_token},
         max_new_tokens=400,
         device_map="auto",