Commit Graph

372 Commits

Author SHA1 Message Date
mrq
6676c89c0e I sucked off the hyptothetical wizard again, just using BNB's ADAM optimizer nets HUGE savings, but I don't know the output costs, will need to test 2023-02-23 02:42:17 +00:00
mrq
4427d7fb84 initial conversion (errors out) 2023-02-22 23:07:05 +00:00
mrq
535549c3f3 add some snark about the kludge I had to fix, and the kludge I used to fix it 2023-02-17 19:20:19 +00:00
mrq
94d0f16608 Necessary fixes to get it to work 2023-02-17 02:03:00 +00:00
James Betker
f31a333c4f more sampling fixes 2022-10-10 20:11:28 -06:00
James Betker
5d172fbf7e Fix eval 2022-10-10 14:22:36 -06:00
James Betker
cc74a43675 Checkin 2022-10-10 11:30:20 -06:00
James Betker
27a9b1b750 rename perplexity->log perplexity 2022-07-28 09:48:40 -06:00
James Betker
4509cfc705 track logperp for diffusion evals 2022-07-28 01:30:44 -06:00
James Betker
a1bbde8a43 few things 2022-07-26 11:52:03 -06:00
James Betker
f8108cfdb2 update environment and fix a bunch of deps 2022-07-24 23:43:25 -06:00
James Betker
cc62ba9cba few more tfd13 things 2022-07-24 17:39:33 -06:00
James Betker
f3d967dbf5 remove eta from mdf 2022-07-24 17:21:20 -06:00
James Betker
76464ca063 some fixes to mdf to support new archs 2022-07-21 10:55:50 -06:00
James Betker
13c263e9fb go all in on m2wv3 2022-07-21 00:51:27 -06:00
James Betker
ee8ceed6da rework tfd13 further
- use a gated activation layer for both attention & convs
- add a relativistic learned position bias. I believe this is similar to the T5 position encodings but it is simpler and learned
- get rid of prepending to the attention matrix - this doesn't really work that well. the model eventually learns to attend one of its heads to these blocks but why not just concat if it is doing that?
2022-07-20 23:28:29 -06:00
James Betker
82bd62019f diffuse the cascaded prior for continuous sr model 2022-07-20 11:54:09 -06:00
James Betker
b0e3be0a17 transition to nearest interpolation mode for downsampling 2022-07-20 10:56:17 -06:00
James Betker
15decfdb98 misc 2022-07-20 10:19:02 -06:00
James Betker
2997a640b0 fix mdf 2022-07-19 19:39:29 -06:00
James Betker
fc0b291b21 do masking up proper 2022-07-19 16:32:17 -06:00
James Betker
b203a7dc97 And remove unused parameters 2022-07-19 15:05:12 -06:00
James Betker
17a07b2e33 readd one mdf function 2022-07-19 15:04:36 -06:00
James Betker
b157b28c7b tfd14
hopefully this helps address the positional dependencies of tfd12
2022-07-19 13:30:05 -06:00
James Betker
1b6fe88bcb spit out overages in GDI 2022-07-19 11:19:59 -06:00
James Betker
da9e47ca0e new bounds for MEL normalization and multi-resolution SR in MDF 2022-07-19 11:11:46 -06:00
James Betker
2fb85526bc mdf cleanup 2022-07-19 09:57:05 -06:00
James Betker
4aa840a494 be more stringent on min and max ranges in GDI.. this is gonna break somethings probably 2022-07-19 09:14:08 -06:00
James Betker
8d7692c1e0 uh 2022-07-18 17:15:27 -06:00
James Betker
83a4ef4149 default to use input for conditioning & add preprocessed input to GDI 2022-07-18 17:01:19 -06:00
James Betker
1b4d9567f3 tfd13 for multi-resolution superscaling 2022-07-18 16:36:22 -06:00
James Betker
20ef9cc6b4 iq checkin
yeah - I'm at it again...
2022-07-17 18:24:33 -06:00
James Betker
438dcaccc5 misc 2022-07-16 13:58:52 -06:00
James Betker
51291ab070 Some additional context regularization in tfd 2022-07-14 21:49:47 -06:00
James Betker
7170ccdfa9 Merge branch 'baktfd' 2022-07-14 21:38:45 -06:00
James Betker
3b12d348fc mdf: provide conditioning margin 2022-07-14 21:38:14 -06:00
James Betker
4d53c66602 simplify span selecting logic in tfdpc 2022-07-14 21:25:03 -06:00
James Betker
def70cd444 Merge remote-tracking branch 'origin/master' 2022-07-13 21:26:59 -06:00
James Betker
711c53c1f0 music script 2022-07-13 21:26:55 -06:00
James Betker
15831b2576 some stuff 2022-07-13 21:26:25 -06:00
James Betker
f46d6645da tfdpcv5 updates 2022-07-12 21:48:18 -06:00
James Betker
ce82eb6022 update MDF for ar prior diffusion 2022-07-11 17:03:56 -06:00
James Betker
3edca1a906 Rescale causal scale along with timestep spacing 2022-07-09 22:09:25 -06:00
James Betker
b432d7c7de mdf: re-allow p_sample_loop 2022-07-09 15:35:09 -06:00
James Betker
79a5b54e57 :( 2022-07-09 08:15:02 -06:00
James Betker
99adc846c7 Restore causal decoding 2022-07-09 08:11:08 -06:00
James Betker
5138d61767 Restore old MDF functionality for cheater gen 2022-07-09 08:01:32 -06:00
James Betker
55b9f31825 fix mel outputs 2022-07-08 19:51:12 -06:00
James Betker
b99af89c8f Support causal diffusion in inference 2022-07-08 14:27:19 -06:00
James Betker
ba1699cee2 Improve mdf 2022-07-08 12:30:22 -06:00