Manuel Romero

Results 8 comments of Manuel Romero

Great work! Can big models such us models used in the example colab be fine-tuned just loading it as `int8`? Are you thinking about release a colab for fine-tuning a...

I will check the Colab

Sorry, guys. I forgot this issue. NLP is kind of hobby and I don't have too much free time lately. I will search the Colab and I will share it...

Thank you. I was thinking doing something like that.

When I trained Electra small on my Spanish corpus the loss was shown if trained on GPU. Now, I got access to TFRC and trained it using its TPUs pod...

Can I help with this, @patrickvonplaten ?

Sorry, I have been busy. I will start this weekend.

What about something like this to start from basics examples? https://colab.research.google.com/drive/1wNcIBklvOTBvsUXcUU_z4sDQFEf6w9u9