mirror of https://github.com/THUDM/ChatGLM-6B
111 lines
4.0 KiB
Python
111 lines
4.0 KiB
Python
from transformers import AutoModel, AutoTokenizer
|
||
import gradio as gr
|
||
import mdtex2html
|
||
import MultiDevices
|
||
tokenizer = AutoTokenizer.from_pretrained("THUDM/ChatGLM-6B", trust_remote_code=True)
|
||
model = AutoModel.from_pretrained("THUDM/ChatGLM-6B", trust_remote_code=True).half()
|
||
MultiDevices.GPU_precision = 'int8'
|
||
MultiDevices.embeddings = 'cpu'
|
||
#默认为使用6G显存+16G内存，修改请参阅https://github.com/ChaimEvans/ChatGLM_MultiGPUCPU_eval根据显存合理配置显卡和CPU的负载大小。
|
||
MultiDevices.layers={
|
||
'cuda:0': '1-20',
|
||
'cpu':'21-28'
|
||
}
|
||
MultiDevices.final_layernorm = 'cpu'
|
||
model = MultiDevices.ConfigMultiDevices(model)
|
||
model = model.eval()
|
||
|
||
"""Override Chatbot.postprocess"""
|
||
|
||
|
||
def postprocess(self, y):
|
||
if y is None:
|
||
return []
|
||
for i, (message, response) in enumerate(y):
|
||
y[i] = (
|
||
None if message is None else mdtex2html.convert((message)),
|
||
None if response is None else mdtex2html.convert(response),
|
||
)
|
||
return y
|
||
|
||
|
||
gr.Chatbot.postprocess = postprocess
|
||
|
||
|
||
def parse_text(text):
|
||
"""copy from https://github.com/GaiZhenbiao/ChuanhuChatGPT/"""
|
||
lines = text.split("\n")
|
||
lines = [line for line in lines if line != ""]
|
||
count = 0
|
||
for i, line in enumerate(lines):
|
||
if "```" in line:
|
||
count += 1
|
||
items = line.split('`')
|
||
if count % 2 == 1:
|
||
lines[i] = f'<pre><code class="language-{items[-1]}">'
|
||
else:
|
||
lines[i] = f'<br></code></pre>'
|
||
else:
|
||
if i > 0:
|
||
if count % 2 == 1:
|
||
line = line.replace("`", "\`")
|
||
line = line.replace("<", "<")
|
||
line = line.replace(">", ">")
|
||
line = line.replace(" ", " ")
|
||
line = line.replace("*", "*")
|
||
line = line.replace("_", "_")
|
||
line = line.replace("-", "-")
|
||
line = line.replace(".", ".")
|
||
line = line.replace("!", "!")
|
||
line = line.replace("(", "(")
|
||
line = line.replace(")", ")")
|
||
line = line.replace("$", "$")
|
||
lines[i] = "<br>"+line
|
||
text = "".join(lines)
|
||
return text
|
||
|
||
|
||
def predict(input, chatbot, max_length, top_p, temperature, history):
|
||
chatbot.append((parse_text(input), ""))
|
||
for response, history in model.stream_chat(tokenizer, input, history, max_length=max_length, top_p=top_p,
|
||
temperature=temperature):
|
||
chatbot[-1] = (parse_text(input), parse_text(response))
|
||
|
||
yield chatbot, history
|
||
|
||
|
||
def reset_user_input():
|
||
return gr.update(value='')
|
||
|
||
|
||
def reset_state():
|
||
return [], []
|
||
|
||
|
||
with gr.Blocks() as demo:
|
||
gr.HTML("""<h1 align="center">ChatGLM</h1>""")
|
||
|
||
chatbot = gr.Chatbot()
|
||
with gr.Row():
|
||
with gr.Column(scale=4):
|
||
with gr.Column(scale=12):
|
||
user_input = gr.Textbox(show_label=False, placeholder="Input...", lines=10).style(
|
||
container=False)
|
||
with gr.Column(min_width=32, scale=1):
|
||
submitBtn = gr.Button("Submit", variant="primary")
|
||
with gr.Column(scale=1):
|
||
emptyBtn = gr.Button("Clear History")
|
||
max_length = gr.Slider(0, 4096, value=2048, step=1.0, label="Maximum length", interactive=True)
|
||
top_p = gr.Slider(0, 1, value=0.7, step=0.01, label="Top P", interactive=True)
|
||
temperature = gr.Slider(0, 1, value=0.95, step=0.01, label="Temperature", interactive=True)
|
||
|
||
history = gr.State([])
|
||
|
||
submitBtn.click(predict, [user_input, chatbot, max_length, top_p, temperature, history], [chatbot, history],
|
||
show_progress=True)
|
||
submitBtn.click(reset_user_input, [], [user_input])
|
||
|
||
emptyBtn.click(reset_state, outputs=[chatbot, history], show_progress=True)
|
||
|
||
demo.queue().launch(share=False, inbrowser=True)
|