mirror of https://github.com/THUDM/ChatGLM2-6B
Init commit
duzx16
commit
057afcce19
|
|
@ -0,0 +1,59 @@
|
|||
import os
|
||||
import platform
|
||||
import signal
|
||||
from transformers import AutoTokenizer, AutoModel
|
||||
import readline
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("/mnt/vepfs/workspace/zxdu/chatglm-6b-v2-dev", trust_remote_code=True)
|
||||
model = AutoModel.from_pretrained("/mnt/vepfs/workspace/zxdu/chatglm-6b-v2-dev", trust_remote_code=True, device='cuda')
|
||||
model = model.eval()
|
||||
|
||||
os_name = platform.system()
|
||||
clear_command = 'cls' if os_name == 'Windows' else 'clear'
|
||||
stop_stream = False
|
||||
|
||||
|
||||
def build_prompt(history):
|
||||
prompt = "欢迎使用 ChatGLM-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序"
|
||||
for query, response in history:
|
||||
prompt += f"\n\n用户：{query}"
|
||||
prompt += f"\n\nChatGLM-6B：{response}"
|
||||
return prompt
|
||||
|
||||
|
||||
def signal_handler(signal, frame):
|
||||
global stop_stream
|
||||
stop_stream = True
|
||||
|
||||
|
||||
def main():
|
||||
past_key_values, history = None, []
|
||||
global stop_stream
|
||||
print("欢迎使用 ChatGLM-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
|
||||
while True:
|
||||
query = input("\n用户：")
|
||||
if query.strip() == "stop":
|
||||
break
|
||||
if query.strip() == "clear":
|
||||
past_key_values, history = None, []
|
||||
os.system(clear_command)
|
||||
print("欢迎使用 ChatGLM-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
|
||||
continue
|
||||
count = 0
|
||||
for response, history, past_key_values in model.stream_chat(tokenizer, query, history=history,
|
||||
past_key_values=past_key_values):
|
||||
if stop_stream:
|
||||
stop_stream = False
|
||||
break
|
||||
else:
|
||||
count += 1
|
||||
if count % 8 == 0:
|
||||
os.system(clear_command)
|
||||
print(build_prompt(history), flush=True)
|
||||
signal.signal(signal.SIGINT, signal_handler)
|
||||
os.system(clear_command)
|
||||
print(build_prompt(history), flush=True)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
|
@ -0,0 +1,102 @@
|
|||
from transformers import AutoModel, AutoTokenizer
|
||||
import gradio as gr
|
||||
import mdtex2html
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("/mnt/vepfs/workspace/zxdu/chatglm-6b-v2-dev", trust_remote_code=True)
|
||||
model = AutoModel.from_pretrained("/mnt/vepfs/workspace/zxdu/chatglm-6b-v2-dev", trust_remote_code=True, device='cuda')
|
||||
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, past_key_values):
|
||||
chatbot.append((parse_text(input), ""))
|
||||
for response, history, past_key_values in model.stream_chat(tokenizer, input, history, past_key_values=past_key_values,
|
||||
max_length=max_length, top_p=top_p, temperature=temperature):
|
||||
chatbot[-1] = (parse_text(input), parse_text(response))
|
||||
|
||||
yield chatbot, history, past_key_values
|
||||
|
||||
|
||||
def reset_user_input():
|
||||
return gr.update(value='')
|
||||
|
||||
|
||||
def reset_state():
|
||||
return [], [], None
|
||||
|
||||
|
||||
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([])
|
||||
past_key_values = gr.State(None)
|
||||
|
||||
submitBtn.click(predict, [user_input, chatbot, max_length, top_p, temperature, history, past_key_values],
|
||||
[chatbot, history, past_key_values], show_progress=True)
|
||||
submitBtn.click(reset_user_input, [], [user_input])
|
||||
|
||||
emptyBtn.click(reset_state, outputs=[chatbot, history, past_key_values], show_progress=True)
|
||||
|
||||
demo.queue().launch(share=False, inbrowser=True)
|
||||
Loading…
Reference in New Issue