from transformers import AutoTokenizer, AutoModel
import time
tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm3-6b", trust_remote_code=True)
model = AutoModel.from_pretrained("THUDM/chatglm3-6b", trust_remote_code=True).half().cuda()
model = model.eval()
# response, history = model.chat(tokenizer, "你好", history=[])
# print(response)
# response, history = model.chat(tokenizer, "晚上睡不着应该怎么办", history=history)
# print(response)
# 使用 range 函数生成一个从0到9的整数序列,共10个数字
for i in range(10):
# 在这里写入需要循环执行的代码
a = time.time()
response, history = model.chat(tokenizer, "写一篇秋天的文章,不少于1000字", history=[])
print(response)
print(time.time()-a)
GPU运行Huggingface的大模型THUDM/chatglm3-6b
最新推荐文章于 2024-07-29 14:37:54 发布