web_demo2.py 3.13 KB
Newer Older
1
2
3
4
5
6
7
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)
8
9
DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
# 设置页面标题、图标和布局
10
st.set_page_config(
11
    page_title="ChatGLM3-6B 演示",
12
13
14
15
16
17
18
    page_icon=":robot:",
    layout="wide"
)

@st.cache_resource
def get_model():
    tokenizer = AutoTokenizer.from_pretrained(TOKENIZER_PATH, trust_remote_code=True)
19
20
21
22
23
24
25
    if 'cuda' in DEVICE:  # AMD, NVIDIA GPU can use Half Precision
        model = AutoModel.from_pretrained(MODEL_PATH, trust_remote_code=True).to(DEVICE).eval()
    else:  # CPU, Intel GPU and other GPU can use Float16 Precision Only
        model = AutoModel.from_pretrained(MODEL_PATH, trust_remote_code=True).float().to(DEVICE).eval()
    # 多显卡支持,使用下面两行代替上面一行,将num_gpus改为你实际的显卡数量
    # from utils import load_model_on_gpus
    # model = load_model_on_gpus("THUDM/chatglm3-6b", num_gpus=2)
26
27
28
29
30
    return tokenizer, model

# 加载Chatglm3的model和tokenizer
tokenizer, model = get_model()

31
# 初始化历史记录和past key values
32
33
34
35
36
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

37
# 设置max_length、top_p和temperature
38
39
40
41
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)

42
# 清理会话历史
43
44
45
46
47
48
49
50
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()

51
# 渲染聊天历史记录
52
53
54
55
56
57
58
59
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"])

60
# 输入框和输出框
61
62
63
64
65
with st.chat_message(name="user", avatar="user"):
    input_placeholder = st.empty()
with st.chat_message(name="assistant", avatar="assistant"):
    message_placeholder = st.empty()

66
# 获取用户输入
67
prompt_text = st.chat_input("请输入您的问题")
68
69

# 如果用户输入了内容,则生成回复
70
if prompt_text:
71

72
73
74
75
    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(
76
77
78
79
80
81
82
83
        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,
84
85
    ):
        message_placeholder.markdown(response)
86
87

    # 更新历史记录和past key values
88
89
    st.session_state.history = history
    st.session_state.past_key_values = past_key_values