wehub-resource-sync
87 lines
2.9 KiB
Python
87 lines
2.9 KiB
Python
"""
|
|
This script is a simple web demo based on Streamlit, showcasing the use of the ChatGLM3-6B model. For a more comprehensive web demo,
|
|
it is recommended to use 'composite_demo'.
|
|
|
|
Usage:
|
|
- Run the script using Streamlit: `streamlit run web_demo_streamlit.py`
|
|
- Adjust the model parameters from the sidebar.
|
|
- Enter questions in the chat input box and interact with the ChatGLM3-6B model.
|
|
|
|
Note: Ensure 'streamlit' and 'transformers' libraries are installed and the required model checkpoints are available.
|
|
"""
|
|
|
|
import os
|
|
import streamlit as st
|
|
import torch
|
|
from transformers import AutoModel, AutoTokenizer
|
|
|
|
MODEL_PATH = os.environ.get('MODEL_PATH', 'THUDM/chatglm3-6b')
|
|
TOKENIZER_PATH = os.environ.get("TOKENIZER_PATH", MODEL_PATH)
|
|
|
|
st.set_page_config(
|
|
page_title="ChatGLM3-6B Streamlit Simple Demo",
|
|
page_icon=":robot:",
|
|
layout="wide"
|
|
)
|
|
|
|
|
|
@st.cache_resource
|
|
def get_model():
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(TOKENIZER_PATH, trust_remote_code=True)
|
|
model = AutoModel.from_pretrained(MODEL_PATH, trust_remote_code=True, device_map="auto").eval()
|
|
return tokenizer, model
|
|
|
|
|
|
# 加载Chatglm3的model和tokenizer
|
|
tokenizer, model = get_model()
|
|
|
|
if "history" not in st.session_state:
|
|
st.session_state.history = []
|
|
if "past_key_values" not in st.session_state:
|
|
st.session_state.past_key_values = None
|
|
|
|
max_length = st.sidebar.slider("max_length", 0, 32768, 8192, step=1)
|
|
top_p = st.sidebar.slider("top_p", 0.0, 1.0, 0.8, step=0.01)
|
|
temperature = st.sidebar.slider("temperature", 0.0, 1.0, 0.6, step=0.01)
|
|
|
|
buttonClean = st.sidebar.button("清理会话历史", key="clean")
|
|
if buttonClean:
|
|
st.session_state.history = []
|
|
st.session_state.past_key_values = None
|
|
if torch.cuda.is_available():
|
|
torch.cuda.empty_cache()
|
|
st.rerun()
|
|
|
|
for i, message in enumerate(st.session_state.history):
|
|
if message["role"] == "user":
|
|
with st.chat_message(name="user", avatar="user"):
|
|
st.markdown(message["content"])
|
|
else:
|
|
with st.chat_message(name="assistant", avatar="assistant"):
|
|
st.markdown(message["content"])
|
|
|
|
with st.chat_message(name="user", avatar="user"):
|
|
input_placeholder = st.empty()
|
|
with st.chat_message(name="assistant", avatar="assistant"):
|
|
message_placeholder = st.empty()
|
|
|
|
prompt_text = st.chat_input("请输入您的问题")
|
|
if prompt_text:
|
|
input_placeholder.markdown(prompt_text)
|
|
history = st.session_state.history
|
|
past_key_values = st.session_state.past_key_values
|
|
for response, history, past_key_values in model.stream_chat(
|
|
tokenizer,
|
|
prompt_text,
|
|
history,
|
|
past_key_values=past_key_values,
|
|
max_length=max_length,
|
|
top_p=top_p,
|
|
temperature=temperature,
|
|
return_past_key_values=True,
|
|
):
|
|
message_placeholder.markdown(response)
|
|
st.session_state.history = history
|
|
st.session_state.past_key_values = past_key_values
|