[spam] [personal] perceiver model notes
Undiscussed Horrific Abuse, One Victim & Survivor of
gmkarl at gmail.com
Thu Jan 27 05:17:25 PST 2022
this commit finally produces the correct perceiver output without bailing.
i might like to do the gpt2 model next. since i ran into a lot of
unexpected difficulties here.
commit ab72f4a6a2a9095587b02c262ae1b20801172315 (HEAD ->
memory-efficient-attention, xloem/memory-efficient-attention)
Author: xloem <0xloem at gmail.com>
Date: Thu Jan 27 13:14:23 2022 +0000
handle missing attention mask, add code for head_mask, comment out
debugging break
More information about the cypherpunks
mailing list