File size: 3,989 Bytes
561faf0 8c7f129 561faf0 8c7f129 561faf0 2cec527 561faf0 bc5544c 561faf0 bc5544c 8c7f129 f727ca3 af55e76 296ef5c e783c56 af55e76 5f35869 561faf0 296ef5c 561faf0 9193677 561faf0 |
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 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 |
import streamlit as st
import replicate
import os
# App title
st.set_page_config(page_title="🦙💬 Meta Llama Inference")
# Replicate Credentials
with st.sidebar:
st.title('🦙💬 Meta Llama Inference')
if 'REPLICATE_API_TOKEN' in st.secrets:
st.success('API key already provided!', icon='✅')
replicate_api = st.secrets['REPLICATE_API_TOKEN']
else:
replicate_api = st.text_input('Enter Replicate API token:', type='password')
if not (replicate_api.startswith('r8_') and len(replicate_api)==40):
st.warning('Please enter your credentials!', icon='⚠️')
else:
st.success('Proceed to entering your prompt message!', icon='👉')
os.environ['REPLICATE_API_TOKEN'] = replicate_api
st.subheader('Models and parameters')
selected_model = st.sidebar.selectbox('Choose a Meta Llama model', ['Llama2-7B', 'Llama2-13B', 'Llama3-8B-Instruct', 'Llama3-70B-Instruct'], key='selected_model')
if selected_model == 'Llama2-7B':
llm = 'meta/llama-2-7b-chat'
elif selected_model == 'Llama2-13B':
llm = 'meta/llama-2-13b-chat'
elif selected_model == 'Llama3-8B-Instruct':
llm = 'meta/meta-llama-3-8b-instruct'
elif selected_model == 'Llama3-70B-Instruct':
llm = 'meta/meta-llama-3-70b-instruct'
st.sidebar.subheader("System Prompt")
user_input = st.sidebar.text_area("Context for Fine-tuning:", placeholder="e.g. You are a Space Mission Analyst...", height=10)
temperature = st.sidebar.slider('temperature', min_value=0.01, max_value=1.0, 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=1000, value=400, step=8)
#st.markdown('📖 Learn how to build this app in this [blog](https://blog.streamlit.io/how-to-build-a-llama-2-chatbot/)!')
# 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. Refactored from https://github.com/a16z-infra/llama2-chatbot
def generate_llama2_response(prompt_input):
string_dialogue = user_input
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) |