File size: 3,361 Bytes
ea6a8cd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 |
import streamlit as st
import os
# App title
st.set_page_config(page_title="🦙💬 Llama 2 Chatbot")
# 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', '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=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():
st.session_state.messages = [{"role": "assistant", "content": "How may I assist you today?"}]
# Display or clear chat messages
for message in st.session_state.messages:
with st.chat_message(message["role"]):
st.write(message["content"])
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
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:
if dict_message["role"] == "user":
string_dialogue += "User: " + dict_message["content"] + "\n\n"
else:
string_dialogue += "Assistant: " + dict_message["content"] + "\n\n"
# 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
# User-provided prompt
if prompt := st.chat_input(disabled=not replicate_api):
st.session_state.messages.append({"role": "user", "content": prompt})
with st.chat_message("user"):
st.write(prompt)
# Generate a new response if last message is not from assistant
if st.session_state.messages[-1]["role"] != "assistant":
with st.chat_message("assistant"):
with st.spinner("Thinking..."):
response = generate_llama2_response(prompt)
placeholder = st.empty()
full_response = ''
for item in response:
full_response += item
placeholder.markdown(full_response)
placeholder.markdown(full_response)
message = {"role": "assistant", "content": full_response}
st.session_state.messages.append(message) |