Spaces:
Paused
Paused
File size: 2,797 Bytes
4721aa1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 |
import os
import platform
from transformers import AutoTokenizer, AutoModel
import torch
MODEL_PATH = os.environ.get('MODEL_PATH', 'THUDM/chatglm3-6b')
TOKENIZER_PATH = os.environ.get("TOKENIZER_PATH", MODEL_PATH)
DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'
# for Mac Computer like M1
# You Need Use Pytorch compiled with Metal
# DEVICE = 'mps'
# for AMD gpu likes MI100 (Not Official Steady Support yet)
# You Need Use Pytorch compiled with ROCm
# DEVICE = 'cuda'
# for Intel gpu likes A770 (Not Official Steady Support yet)
# You Need Use Pytorch compiled with oneDNN and install intel-extension-for-pytorch
# import intel_extension_for_pytorch as ipex
# DEVICE = 'xpu'
# for Moore Threads gpu like MTT S80 (Not Official Steady Support yet)
# You Need Use Pytorch compiled with Musa
# DEVICE = 'musa'
tokenizer = AutoTokenizer.from_pretrained(TOKENIZER_PATH, trust_remote_code=True)
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()
os_name = platform.system()
clear_command = 'cls' if os_name == 'Windows' else 'clear'
stop_stream = False
welcome_prompt = "欢迎使用 ChatGLM3-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序"
def build_prompt(history):
prompt = welcome_prompt
for query, response in history:
prompt += f"\n\n用户：{query}"
prompt += f"\n\nChatGLM3-6B：{response}"
return prompt
def main():
past_key_values, history = None, []
global stop_stream
print(welcome_prompt)
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(welcome_prompt)
continue
print("\nChatGLM：", end="")
current_length = 0
for response, history, past_key_values in model.stream_chat(tokenizer, query, history=history, top_p=1,
temperature=0.01,
past_key_values=past_key_values,
return_past_key_values=True):
if stop_stream:
stop_stream = False
break
else:
print(response[current_length:], end="", flush=True)
current_length = len(response)
print("")
if __name__ == "__main__":
main()
|