|
|
|
|
|
from transformers import AutoModel, AutoTokenizer |
|
import streamlit as st |
|
from streamlit_chat import message |
|
from fastllm_pytools import llm |
|
from huggingface_hub import snapshot_download,hf_hub_download |
|
|
|
os.system("git clone --recurse-submodules https://github.com/ztxz16/fastllm.git") |
|
os.system("cd fastllm; mkdir build; cd build; cmake ..; make -j; cd tools; python setup.py install --user --prefix=") |
|
|
|
hf_hub_download(repo_id="huangyuyang/chatglm2-6b-int4.flm",local_dir="./", filename="chatglm2-6b-int4.flm") |
|
|
|
st.set_page_config( |
|
page_title="玉刚四号-演示", |
|
page_icon=":robot:", |
|
layout='wide' |
|
) |
|
|
|
|
|
@st.cache_resource |
|
def get_model(): |
|
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True) |
|
model = llm.model("chatglm2-6b-int4.flm") |
|
|
|
return tokenizer, model |
|
|
|
|
|
MAX_TURNS = 20 |
|
MAX_BOXES = MAX_TURNS * 2 |
|
|
|
|
|
def predict(input, max_length, top_p, temperature, history=None): |
|
tokenizer, model = get_model() |
|
if history is None: |
|
history = [] |
|
|
|
with container: |
|
if len(history) > 0: |
|
if len(history)>MAX_BOXES: |
|
history = history[-MAX_TURNS:] |
|
for i, (query, response) in enumerate(history): |
|
message(query, avatar_style="big-smile", key=str(i) + "_user") |
|
message(response, avatar_style="bottts", key=str(i)) |
|
|
|
message(input, avatar_style="big-smile", key=str(len(history)) + "_user") |
|
st.write("AI正在回复:") |
|
with st.empty(): |
|
for response, history in model.stream_chat(tokenizer, input, history, max_length=max_length, top_p=top_p, |
|
temperature=temperature): |
|
query, response = history[-1] |
|
st.write(response) |
|
|
|
return history |
|
|
|
|
|
container = st.container() |
|
|
|
|
|
prompt_text = st.text_area(label="用户命令输入", |
|
height = 100, |
|
placeholder="请在这儿输入您的命令") |
|
|
|
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, 0.95, step=0.01 |
|
) |
|
|
|
if 'state' not in st.session_state: |
|
st.session_state['state'] = [] |
|
|
|
if st.button("发送", key="predict"): |
|
with st.spinner("AI正在思考，请稍等........"): |
|
|
|
st.session_state["state"] = predict(prompt_text, max_length, top_p, temperature, st.session_state["state"]) |
|
|
