Commit Graph

857 Commits

Author SHA1 Message Date
4aa842eada Merge commit 'refs/pull/180/head' of https://github.com/ebolam/KoboldAI into united 2022-09-27 19:29:05 -04:00
be719a7e5e Fix for loading models that don't support breakmodel (GPU/CPU support in UI) 2022-09-27 19:02:37 -04:00
52e120c706 Disable breakmodel if we error on the check 2022-09-28 01:00:06 +02:00
d2ff32be32 Merge pull request #220 from ebolam/united
Fix for loading models on CPU only that don't support breakmodel
2022-09-28 00:46:37 +02:00
057ddb4fb2 Better --cpu handling 2022-09-28 00:45:17 +02:00
168ae8083c Remove debug print 2022-09-27 18:30:20 -04:00
0311cc215e Fix for loading models on CPU only that don't support breakmodel 2022-09-27 18:29:32 -04:00
edd50fc809 Fix for GPT2 breakmodel in the UI 2022-09-27 17:58:51 -04:00
f1d63f61f3 Syntax fix 2022-09-27 22:43:09 +02:00
908dc8ea60 Fix for older model loading 2022-09-27 15:59:56 -04:00
62921c4896 getmodelname for configname 2022-09-27 21:11:31 +02:00
60d09899ea Don't use Fast tokenizers when we don't have to 2022-09-27 18:26:13 +02:00
11455697ef Tokenizer Fixes (Slow first to keep coherency) 2022-09-27 17:57:18 +02:00
07896867b2 Revert Tokenizer Change 2022-09-27 15:36:08 +02:00
82a250aa1b Revert "Fix tokenizer selection code"
This reverts commit 7fba1fd28a.
2022-09-27 15:33:08 +02:00
79ae0f17ec Merge branch 'main' into merge 2022-09-26 16:10:10 -04:00
7fba1fd28a Fix tokenizer selection code 2022-09-26 14:37:25 -04:00
c88f88f54d Merge pull request #215 from ebolam/united
Update for horde selection to pull models automatically
2022-09-25 19:50:44 +02:00
1f6861d55c Update for horde selection to pull models automatically (or on typing with a 1 second delay 2022-09-25 13:49:02 -04:00
d7ed577bf7 Don't stream in chatmode 2022-09-25 17:26:52 +02:00
465c1fd64d 1.19 version bump and polish 2022-09-25 17:00:33 +02:00
ba85ae4527 WI Improvements 2022-09-25 11:13:57 +02:00
d4b7705095 Merge branch 'main' into united 2022-09-24 22:14:32 +02:00
819bd8a78d Fix saving of sharded HF models on non-Windows operating systems 2022-09-24 15:55:53 -04:00
c66657ef1b Flaskwebgui removal 2 2022-09-23 14:46:02 +02:00
557f7fc0fc Remove flaskwebgui (Conflicts with our threading) 2022-09-23 14:45:47 +02:00
2ec7e1c5da Continue if webbrowser fails to open 2022-09-23 14:24:57 +02:00
e68f284006 show_budget fix 2022-09-21 17:53:16 +02:00
d0664207e8 Sync and save show budget 2022-09-21 17:39:56 +02:00
d1d23b5383 New Models 2022-09-20 18:12:54 +02:00
802758cf44 New models 2022-09-20 16:58:59 +02:00
ac0bc1c020 New models 2022-09-19 01:55:12 +02:00
4362ca4b34 fix previously saved settings overwriting new API key 2022-09-16 16:23:04 +02:00
9582722c2e fix model loading format bleeding into gui 2022-09-16 00:08:59 +02:00
e8e0ad85be Merge branch 'united' into dependency-fix 2022-09-15 17:41:34 -04:00
c288c39de7 Remove type hints from http_get 2022-09-15 17:39:32 -04:00
943614b5e6 Merge branch 'main' into dependency-fix 2022-09-15 17:33:48 -04:00
463bf86bcc aria2_hook now uses new cache format if you have transformers 4.22 2022-09-15 16:50:43 -04:00
a75351668f switched model retrieval and sendtocluster to loguru 2022-09-12 17:22:27 +02:00
9280102cb3 Moved Flask Startup into __main__
This allows command line arguments to be parsed first
2022-09-12 17:00:30 +02:00
6bc702854f added verbosity controls 2022-09-12 16:47:10 +02:00
68aaef9090 escapig gen/prompt logs so that they stay in one line 2022-09-12 11:49:59 +02:00
d30bbd28a1 logger for prompt and gen 2022-09-12 01:57:41 +02:00
66ae5c35c0 replaced all warnings with logger 2022-09-12 01:18:25 +02:00
5692e5ce16 finished all init messages 2022-09-12 01:13:12 +02:00
656e3995f0 model tensors info 2022-09-12 01:09:21 +02:00
48f6b5a939 more init messages 2022-09-12 01:00:03 +02:00
4817a27552 multicolored init 2022-09-12 00:49:51 +02:00
11eac68676 more init messages 2022-09-12 00:19:51 +02:00
2a8a223473 added init logs 2022-09-11 23:55:48 +02:00