auto former中--is_training, --model_id, --model, --data是什么意思
时间: 2023-10-08 13:08:22 浏览: 249
auto former是一个开源的语言模型训练框架,其命令行工具提供了一些参数,包括:
1. --is_training表示是否为训练模式,可以选择True或False。
2. --model_id表示所使用的预训练模型ID。
3. --model表示所使用的预训练模型的本地路径或者Hugging Face hub路径,可以不输入如果使用--model_id选项。
4. --data表示训练数据集的本地路径或Hugging Face datasets路径。
相关问题
alert http $EXTERNAL_NET any -> $HOME_NET any (msg:"ET PHISHING Successful Mailbox Update Phish 2016-02-17 M2"; flow:to_client,established; http.stat_code; content:"200"; http.content_type; content:"text/html"; startswith; file.data; content:"Your e-mail account will be verify"; nocase; fast_pattern; content:"DO NOT RESEND"; nocase; distance:0; content:"MESSAGE IS FROM THE SYSTEM ADMIN"; nocase; distance:0; classtype:credential-theft; sid:2031968; rev:3; metadata:attack_target Client_Endpoint, created_at 2016_02_17, deployment Perimeter, former_category PHISHING, signature_severity Critical, tag Phishing, updated_at 2020_06_24, mitre_tactic_id TA0001, mitre_tactic_name Initial_Access, mitre_technique_id T1566, mitre_technique_name Phishing;)
这是一条 Suricata IDS/IPS 规则,用于检测钓鱼攻击中的一种成功的邮箱更新诈骗,日期为2016年2月17日。规则的作用是在流量中检测HTTP响应码为200、内容类型为text/html,且以特定文本开头(Your e-mail account will be verify),包含特定文本(DO NOT RESEND和MESSAGE IS FROM THE SYSTEM ADMIN),距离为0,同时设置了多个元数据,如攻击目标、分类、Mitre ATT&CK等信息。如果触发规则,则会被分类为credential-theft类型的攻击,并生成相应的警报。
(env) (base) PS D:\MiniGPT-4> python demo.py --cfg-path eval_configs/minigpt4_eval.yaml Initializing Chat Loading VIT Loading VIT Done Loading Q-Former Traceback (most recent call last): File "D:\MiniGPT-4\env\lib\site-packages\transformers\utils\hub.py", line 409, in cached_file resolved_file = hf_hub_download( File "D:\MiniGPT-4\env\lib\site-packages\huggingface_hub\utils\_validators.py", line 120, in _inner_fn return fn(*args, **kwargs) File "D:\MiniGPT-4\env\lib\site-packages\huggingface_hub\file_download.py", line 1259, in hf_hub_download raise LocalEntryNotFoundError( huggingface_hub.utils._errors.LocalEntryNotFoundError: Connection error, and we cannot find the requested files in the disk cache. Please try again or make sure your Internet connection is on. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "D:\MiniGPT-4\demo.py", line 57, in <module> model = model_cls.from_config(model_config).to('cuda:0') File "D:\MiniGPT-4\minigpt4\models\mini_gpt4.py", line 241, in from_config model = cls( File "D:\MiniGPT-4\minigpt4\models\mini_gpt4.py", line 64, in __init__ self.Qformer, self.query_tokens = self.init_Qformer( File "D:\MiniGPT-4\minigpt4\models\blip2.py", line 47, in init_Qformer encoder_config = BertConfig.from_pretrained("bert-base-uncased") File "D:\MiniGPT-4\env\lib\site-packages\transformers\configuration_utils.py", line 546, in from_pretrained config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs) File "D:\MiniGPT-4\env\lib\site-packages\transformers\configuration_utils.py", line 573, in get_config_dict config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs) File "D:\MiniGPT-4\env\lib\site-packages\transformers\configuration_utils.py", line 628, in _get_config_dict resolved_config_file = cached_file( File "D:\MiniGPT-4\env\lib\site-packages\transformers\utils\hub.py", line 443, in cached_file raise EnvironmentError( OSError: We couldn't connect to 'https://huggingface.co' to load this file, couldn't find it in the cached files and it looks like bert-base-uncased is not the path to a directory containing a file named config.json. Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/transformers/installation#offline-mode'.
这个错误是由于网络连接问题导致无法下载所需的模型和文件。在初始化Chat时,脚本尝试从Hugging Face模型库中下载`Q-Former`模型,但由于无法连接到`https://huggingface.co`,导致下载失败。
请确保你的网络连接正常,并且能够访问`https://huggingface.co`网站。如果你使用的是代理,请确保代理设置正确。
如果你的网络连接正常,但仍然无法下载模型,你可以尝试使用离线模式运行脚本。在离线模式下,你需要手动下载所需的模型和文件,并将它们放置在正确的路径中。你可以参考Hugging Face文档中的离线模式部分了解更多信息。
希望这些提示能帮助你解决问题。如果你有其他疑问,请随时提问。
阅读全文