Timeline for Can the attention mask hold values between 0 and 1?
Current License: CC BY-SA 4.0
14 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
Nov 12 at 1:00 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
Jul 15 at 0:03 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
Mar 16 at 18:02 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
Nov 14, 2023 at 12:09 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
Jul 6, 2023 at 22:07 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
Mar 6, 2023 at 5:00 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
Oct 29, 2022 at 17:10 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
Jun 30, 2022 at 13:07 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
May 25, 2022 at 21:31 | comment | added | neel g |
Hey, welcome to S.E Answers aren't the correct place to ask questions ;) but for your query, lookup soft attention as keyword to start you off
|
|
May 25, 2022 at 18:17 | comment | added | Dave | I also had the same idea, using a floating point attention_mask. Could you please provide some reference where this attention is summed over to compute the sequence lengths? Moreover, in the documentation I see torch.FloatTensor is it casted to LongTensor somewere inside the modules? Thank you very much! | |
Feb 4, 2022 at 4:08 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
Oct 6, 2021 at 2:05 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
May 20, 2021 at 7:16 | answer | added | Jindřich | timeline score: 0 | |
May 16, 2021 at 12:47 | history | asked | neel g | CC BY-SA 4.0 |