介绍

LLM-Detector是一个检测AI/LLMs生成文本内容的检测工具，此仓库模型为Small版本的中文检测模型

快速使用

from modelscope import (
    HubApi, snapshot_download, AutoModelForCausalLM, AutoTokenizer, GenerationConfig
)

model_dir = snapshot_download("QiYuan-tech/LLM-Detector-Small-zh",revision = "v1.0.0")

# Note: The default behavior now has injection attack prevention off.
tokenizer = AutoTokenizer.from_pretrained(model_dir, trust_remote_code=True)

# use auto mode, automatically select precision based on the device.
model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True).eval()
#model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto", trust_remote_code=True).cuda()

response, history = model.chat(tokenizer, "你好", history=None)
print(response)