Update app.py

app.py

@@ -8,7 +8,6 @@ st.set_page_config(page_title="🦙💬 Llama 2 Chatbot")
 # Replicate Credentials
 with st.sidebar:
     st.title('🦙💬 Llama 2 Chatbot')
-    st.write('This chatbot is created using the open-source Llama 2 LLM model from Meta.')
     if 'REPLICATE_API_TOKEN' in st.secrets:
         st.success('API key already provided!', icon='✅')
         replicate_api = st.secrets['REPLICATE_API_TOKEN']
@@ -18,18 +17,23 @@ with st.sidebar:
             st.warning('Please enter your credentials!', icon='⚠️')
         else:
             st.success('Proceed to entering your prompt message!', icon='👉')
-    os.environ['REPLICATE_API_TOKEN'] = replicate_api
 
+    # Refactored from https://github.com/a16z-infra/llama2-chatbot
     st.subheader('Models and parameters')
-    selected_model = st.sidebar.selectbox('Choose a Llama2 model', ['Llama2-7B', 'Llama2-13B'], key='selected_model')
+    selected_model = st.sidebar.selectbox('Choose a Llama2 model', ['Llama2-7B', 'Llama2-13B', 'Llama2-70B'], key='selected_model')
     if selected_model == 'Llama2-7B':
         llm = 'a16z-infra/llama7b-v2-chat:4f0a4744c7295c024a1de15e1a63c880d3da035fa1f49bfd344fe076074c8eea'
     elif selected_model == 'Llama2-13B':
         llm = 'a16z-infra/llama13b-v2-chat:df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5'
+    else:
+        llm = 'replicate/llama70b-v2-chat:e951f18578850b652510200860fc4ea62b3b16fac280f83ff32282f87bbd2e48'
+    
     temperature = st.sidebar.slider('temperature', min_value=0.01, max_value=5.0, value=0.1, step=0.01)
     top_p = st.sidebar.slider('top_p', min_value=0.01, max_value=1.0, value=0.9, step=0.01)
-    max_length = st.sidebar.slider('max_length', min_value=32, max_value=128, value=120, step=8)
+    max_length = st.sidebar.slider('max_length', min_value=64, max_value=4096, value=512, step=8)
+    
     st.markdown('📖 Learn how to build this app in this [blog](https://blog.streamlit.io/how-to-build-a-llama-2-chatbot/)!')
+os.environ['REPLICATE_API_TOKEN'] = replicate_api
 
 # Store LLM generated responses
 if "messages" not in st.session_state.keys():
@@ -44,7 +48,7 @@ def clear_chat_history():
     st.session_state.messages = [{"role": "assistant", "content": "How may I assist you today?"}]
 st.sidebar.button('Clear Chat History', on_click=clear_chat_history)
 
-# Function for generating LLaMA2 response. Refactored from https://github.com/a16z-infra/llama2-chatbot
+# Function for generating LLaMA2 response
 def generate_llama2_response(prompt_input):
     string_dialogue = "You are a helpful assistant. You do not respond as 'User' or pretend to be 'User'. You only respond once as 'Assistant'."
     for dict_message in st.session_state.messages:
@@ -52,7 +56,7 @@ def generate_llama2_response(prompt_input):
             string_dialogue += "User: " + dict_message["content"] + "\n\n"
         else:
             string_dialogue += "Assistant: " + dict_message["content"] + "\n\n"
-    output = replicate.run('a16z-infra/llama13b-v2-chat:df7690f1994d94e96ad9d568eac121aecf50684a0b0963b25a41cc40061269e5', 
+    output = replicate.run(llm, 
                            input={"prompt": f"{string_dialogue} {prompt_input} Assistant: ",
                                   "temperature":temperature, "top_p":top_p, "max_length":max_length, "repetition_penalty":1})
     return output