another1s
another1s
> 应该是依赖没有安装完整,可以按照readme执行 > > ``` > conda create --name gptq python=3.9 -y > conda activate gptq > conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia > # Or,...
> 的colab.notebook的时候, 在最后 我test_kernel就过不了。。。说是要cuda11.7和gcc>=6.0.0才能完成compile
> Hi @another1s , here is an example of creating a subtitle file from scratch: > > ```python > from pysubs2 import SSAFile, SSAEvent, make_time > > subs = SSAFile()...
> 5 hours shouldn't be a problem for the modern hardware. Try smaller model if you don't have GPU with CUDA. i agree, but it just happend and i really...
[my_code.txt](https://github.com/SYSTRAN/faster-whisper/files/14751278/my_code.txt) I only pasted the relevant function here.   the figure above are my gpu info screenshot and a glimpse of output result(too much to paste). the first line...
> [my_code.txt](https://github.com/SYSTRAN/faster-whisper/files/14751278/my_code.txt) I only pasted the relevant function here. > >   the figure above are my gpu info screenshot and a glimpse of output result(too much to paste)....
> > the first line of the result is literally the same as the issue mention in... > > One line of hallucination is nothing to worry about. > >...
> > 咦,那就还是加载失败了,因为QWenTokenizer这个类就是在你修改过的`tokenization_qwen.py`中定义的;按说qwen不会不支持加载本地分词器啊,本地的模型文件目录下面东西是齐的不,`qwen.tiktoken`、`tokenization_qwen.py`、`tokenizer_config.json`啥的都在?这可有点玄学了Orz > > 跑通了!你提到模型目录下的tokenization_qwen.py,我没意识到是这个文件夹下的,我一直改的是c盘下面的那个,不好意思,感谢感谢! 你好你好,遇到了同样的问题,我试图去改transformers/models/qwen2/tokenization_qwen.py里的东西,但发现没有那个在.cache 中的代码?似乎都没有涉及到ttf的内容,请问你是改动了哪个文件呢
> > > > 咦,那就还是加载失败了,因为QWenTokenizer这个类就是在你修改过的`tokenization_qwen.py`中定义的;按说qwen不会不支持加载本地分词器啊,本地的模型文件目录下面东西是齐的不,`qwen.tiktoken`、`tokenization_qwen.py`、`tokenizer_config.json`啥的都在?这可有点玄学了Orz > > > > > > > > > 跑通了!你提到模型目录下的tokenization_qwen.py,我没意识到是这个文件夹下的,我一直改的是c盘下面的那个,不好意思,感谢感谢! > > > > > > 你好你好,遇到了同样的问题,我试图去改transformers/models/qwen2/tokenization_qwen.py里的东西,但发现没有那个在.cache 中的代码?似乎都没有涉及到ttf的内容,请问你是改动了哪个文件呢 > > 就是你下载的模型文件里面的tokenization_qwen.py,29-35行,参考以上 噢我明白了,感谢!