Open luisquintanilla opened 9 months ago
The tokenizer may not be possible because it's what the model expects. However, you should be able to use a different vocabulary.
Blocking Model Builder as well.
cc @zewditu
It appears that we must adhere to a specific version: libtorch-cpu version 1.13.0.1, I think the is the main blocker for GPU usage in Model Builder.
libtorch-cpu version 1.13.0.1
The tokenizer may not be possible because it's what the model expects. However, you should be able to use a different vocabulary.