Robin Li
Robin Li
> > 0 only use CPU for inference > > Are you using just the CPU for inference or CUDA 0 and CPU? I changed code and just use CPU...
code change like:  
> > > > 0 only use CPU for inference > > > > > > > > > Are you using just the CPU for inference or CUDA 0...
> I found that this was due to the tokenizer not having truncation and max_length set correctly. Once I set it for an appropriate amount I never saw this error...