Deleting a branch is permanent. It CANNOT be undone. Continue?
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》
我照着教程做到最后一步执行运行推理脚本显示报错.
能不能弄个视频完整的演示下,
最后能否请大佬出个3分钟实现训练和生成小说文本的教程视频?
谢谢呀
请问是什么错误?
鹏城.盘古模型的训练、推理、下游任务应用示例等可以进一步参考如下项目,包含详细的使用教程。
https://git.openi.org.cn/PCL-Platform.Intelligence/PanGu-Alpha-GPU
https://git.openi.org.cn/PCL-Platform.Intelligence/PanGu-Alpha-Application。
/code/panguAlpha_pytorch/tools/generate_samples_Pangu.py in
178 if name == "main":
179
--> 180 main()
/code/panguAlpha_pytorch/tools/generate_samples_Pangu.py in main()
127
128 initialize_megatron(extra_args_provider=add_text_generate_args,
--> 129 args_defaults={'tokenizer_type': 'GPT2BPETokenizer'})
130
131 # Set up model and load checkpoint.
/code/panguAlpha_pytorch/megatron/initialize.py in initialize_megatron(extra_args_provider, args_defaults, ignore_unknown_args, allow_no_cuda)
48 set_global_variables(extra_args_provider=extra_args_provider,
49 args_defaults=args_defaults,
---> 50 ignore_unknown_args=ignore_unknown_args)
51
52 # torch.distributed initialization
/code/panguAlpha_pytorch/megatron/global_vars.py in set_global_variables(extra_args_provider, args_defaults, ignore_unknown_args)
68 defaults=args_defaults,
69 ignore_unknown_args=ignore_unknown_args)
---> 70 _ = _build_tokenizer(args)
71 _set_tensorboard_writer(args)
72 _set_adlr_autoresume(args)
/code/panguAlpha_pytorch/megatron/global_vars.py in _build_tokenizer(args)
89 global _GLOBAL_TOKENIZER
90 _ensure_var_is_not_initialized(_GLOBAL_TOKENIZER, 'tokenizer')
---> 91 _GLOBAL_TOKENIZER = build_tokenizer(args)
92 return _GLOBAL_TOKENIZER
93
/code/panguAlpha_pytorch/megatron/tokenizer/tokenizer.py in build_tokenizer(args)
40 # assert args.merge_file is not None
41 # tokenizer = _GPT2BPETokenizer(args.vocab_file, args.merge_file)
---> 42 tokenizer = JIEBATokenizer(args.vocab_file)
43 else:
44 raise NotImplementedError('{} tokenizer is not '
/code/panguAlpha_pytorch/megatron/tokenizer/tokenization_jieba.py in init(self, vocab_file, max_len)
42 model_file = vocab_file + ".model"
43 vocab_file = vocab_file + ".vocab"
---> 44 f = open(vocab_file,'r', encoding='utf-8')
45 lines = f.readlines()
46 self.encoder = {}
FileNotFoundError: [Errno 2] No such file or directory: 'megatron/tokenizer/bpe_4w_pcl/vocab.vocab'
按着你3分钟的教程一步步执行,显示说没有这个文件,但是文件在那里,这是什么问题?
这个文件显然是存在的,可能是你代码执行路径的问题,你试着把vocab-file改为全路径。
重新验证了一下,教程是没问题。可能是你代码运行路径不对,你仔细按照教程再操作一遍看看?
谢谢 已解决