vall-e/vall_e/models/retnet.py

from torchscale.architecture.config import RetNetConfig
from torchscale.architecture.retnet import RetNetDecoder
# from retnet import RetNet
somewhat got recurrent forward working (it's as accurate as chunkwise forward: it's not accurate at all), added option to use AMP instead of blanket setting the weight's dtype 2023-09-02 01:58:29 +00:00			`from torchscale.architecture.config import RetNetConfig`
			`from torchscale.architecture.retnet import RetNetDecoder`
restructured some things with the model to remove dead weights 2023-09-21 00:10:59 +00:00			`# from retnet import RetNet`