We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
您好,感谢提供pai-megatron框架,关于qwen分词器,我有下面几点疑问,还望解答,谢谢! 1)请问qwen系列模型(qwen、qwen1.5、qwen2)的词表和分词方式一直都是一样的吗? 2)如果是一样的,为什么会有两个分词器:QwenTokenizer、Qwen2Tokenizer? 3)如果我想用qwen1.5模型,该选择哪个分词器?
The text was updated successfully, but these errors were encountered:
Qwen2Tokenizer看起来是适配了megatron-core的,继承了MegatronTokenizer。
Sorry, something went wrong.
您好,感谢提供pai-megatron框架,关于qwen分词器,我有下面几点疑问,还望解答,谢谢! 1)请问qwen系列模型(qwen、qwen1.5、qwen2)的词表和分词方式一直都是一样的吗? 2)如果是一样的,为什么会有两个分词器:QwenTokenizer、Qwen2Tokenizer? 3)如果我想用qwen1.5模型,该选择哪个分词器? Qwen2Tokenizer看起来是适配了megatron-core的,继承了MegatronTokenizer。
这个继承是必须的吗,QwenTokenizer都没继承,为什么Qwen2Tokenizer开始继承了
在examples/qwen1_5的训练脚本里有,除了run_pretrain_megatron_qwen.sh里面用的llama_tokenizer,其他都用的qwen2tokenizer。 从hf的代码上来看,llama tokenizer和qwen2tokenizer一样,但是pai里面的qwen2tokenizer实现继承了megatron-core做了适配。 qwen用的tiktoken方式,词表也不一样,现在应该都是用qwen2tokenizer了。
No branches or pull requests
您好,感谢提供pai-megatron框架,关于qwen分词器,我有下面几点疑问,还望解答,谢谢!
1)请问qwen系列模型(qwen、qwen1.5、qwen2)的词表和分词方式一直都是一样的吗?
2)如果是一样的,为什么会有两个分词器:QwenTokenizer、Qwen2Tokenizer?
3)如果我想用qwen1.5模型,该选择哪个分词器?
The text was updated successfully, but these errors were encountered: