mirror of https://github.com/THUDM/ChatGLM-6B
64 lines
2.4 KiB
Python
64 lines
2.4 KiB
Python
import os
|
||
import platform
|
||
import signal
|
||
from transformers import AutoTokenizer, AutoModel
|
||
|
||
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
|
||
model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
|
||
# 按需修改，目前只支持 4/8 bit 量化
|
||
#model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().quantize(4).cuda()
|
||
#如果你没有 GPU 硬件的话，也可以在 CPU 上进行推理，但是推理速度会更慢。使用方法如下（需要大概 32GB 内存）
|
||
#model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).float()
|
||
#如果你的内存不足，可以直接加载量化后的模型：
|
||
#model = AutoModel.from_pretrained("THUDM/chatglm-6b-int4",trust_remote_code=True).float()
|
||
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():
|
||
history = []
|
||
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":
|
||
history = []
|
||
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 in model.stream_chat(tokenizer, query, history=history):
|
||
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()
|