[calum-bird]

Please note: this does make use of a remote server, so use with caution. Working on locally-hosted version for anyone with ~48GB of VRAM (and change) to spare.

[syspec]

Wouldn't that much VRAM just be needed for training the model? Not inference?

[calum-bird]

Haha I wish! That's just loading the weights for inference :)

[syspec]

I sense a humblebrag

[calum-bird]

Haha indeed, NLP is fun!