Commit Graph

1465 Commits

Author SHA1 Message Date
somebody c21c1e3dc0 Don't show token usage when max tokens is unknown 2022-08-11 18:22:06 -05:00
somebody a28faa0cb2 Fix author's note token usage 2022-08-11 18:21:49 -05:00
somebody 555ca5fd05 Add token usage indicator 2022-08-11 17:31:12 -05:00
Henk 77e2a7972c Fix incorrect max tokens 2022-08-06 17:28:55 +02:00
Henk 76c7783ac8 Hide useless scrollbars on model list 2022-08-06 17:15:29 +02:00
Henk fe00581b83 Merge branch 'main' into united 2022-08-06 17:10:09 +02:00
Henk c71fd0cc3f OPT Nerys V2 6B 2022-08-06 17:04:22 +02:00
Henk 610257b36e Output Streaming on by Default 2022-08-06 16:47:04 +02:00
Henk fccb464989 Polish 2 2022-08-06 16:43:45 +02:00
Henk 0a0bd75617 Polish 2022-08-06 16:42:15 +02:00
henk717 8bcf4187ac
Merge pull request #178 from one-some/token-prob
Add token probability visualizer
2022-08-05 14:27:46 +02:00
henk717 ed9391431b
Merge pull request #177 from ebolam/united
Fix for secondary model loads leaking settings into secondary model's…
2022-08-05 14:20:25 +02:00
ebolam b484b973d9 Fix for custom model box not showing up in model load menu if there aren't any models in the model folder 2022-08-04 19:26:55 -04:00
somebody f6d046fe1b Add token probability visualizer 2022-08-04 13:49:37 -05:00
henk717 5f1ffc0cd4
Merge branch 'KoboldAI:main' into united 2022-08-04 20:48:31 +02:00
henk717 c753eb24c8
Merge pull request #148 from LightSaveUs/main
Updated ReadMe and 2.7B models descriptions
2022-08-04 20:48:15 +02:00
LightSaveUs c314dde330
Returned the information about chatbot mode 2022-08-03 18:11:59 +03:00
LightSaveUs ee22248855
Updated the readme to reflect current reality 2022-08-03 03:06:18 +03:00
ebolam 71e119f0b7 Fix for secondary model loads leaking settings into secondary model's settings file. 2022-08-02 19:45:36 -04:00
ebolam 7ab39bac0f
Merge pull request #21 from henk717/united
Update to current
2022-08-02 19:38:16 -04:00
LightSaveUs c0d344d125
Fix for 2.7B model names in their descriptions 2022-08-03 01:56:31 +03:00
LightSaveUs c5e0e8a2be
Fix for 2.7B model names in their descriptions 2022-08-03 01:53:49 +03:00
henk717 bd13a41eb7
Merge pull request #176 from one-some/shortcuts
Add editor shortcuts and actually fix streaming newline bug
2022-07-31 12:46:17 +02:00
somebody 59d55369cb Add shortcuts
Adds shortcuts to the UI. These shortcuts are:
Ctrl-Z: Undo
Ctrl-Y: Redo
Ctrl-E: Retry
2022-07-30 21:34:42 -05:00
somebody 5d135e091e Fix the streaming newline bug (for real this time I promise)
After actually investigating the cause of the bug instead of duct taping
a fix on, I have produced a better fix. The previous fix caused a bug
where there a newline was *removed* where it shouldn't have been when
undoing and redoing. The reason this bug was happening in the first
place was because some "newline regulation" code was falsely detecting
the output stream as a text chunk, and attempted to remove a newline
from there instead of the actual chunk.
2022-07-30 21:28:50 -05:00
henk717 56783a1257
Merge pull request #175 from one-some/token-streaming-newline-fix
Fix arbitrary newline insertion when token streaming is enabled
2022-07-31 01:22:15 +02:00
somebody 32ad83df8e Fix arbitrary newline insertion when token streaming is enabled
In adventure mode with token streaming enabled, retrying after an action
would cause a <br> element to be inserted into the action. This prevents
the insertion of the <br> if token streaming is enabled.
2022-07-30 15:05:54 -05:00
henk717 71ea8b215a
Merge branch 'KoboldAI:main' into united 2022-07-30 21:46:25 +02:00
henk717 88e48662a0
Merge pull request #147 from rahulmb/main
Update install_requirements.bat
2022-07-30 21:46:03 +02:00
Rahul Bhandari 15333501ac Update install_requirements.bat
%B% never set and finetuneanon is deprecated
2022-07-30 14:41:15 -05:00
henk717 050e195420
Merge pull request #173 from one-some/token-streaming
Add token streaming option
2022-07-30 18:32:51 +02:00
henk717 a63f7cfa5a
Merge pull request #174 from ebolam/united
Fix for blank model info box when downloading model
2022-07-29 22:15:58 +02:00
ebolam f97c10b794 Fix for blank model info box when downloading model 2022-07-28 19:40:27 -04:00
somebody a4d81292f8 Add token streaming option 2022-07-27 22:13:08 -05:00
henk717 699c2353e7
Merge branch 'KoboldAI:main' into united 2022-07-27 18:06:53 +02:00
henk717 e8a077f072
Merge pull request #146 from VE-FORBRYDERNE/aria2
Fix aria2 in Colab
2022-07-27 18:04:15 +02:00
vfbd 9c8b825b4a aria2 hook now also catches EntryNotFoundError 2022-07-27 11:45:07 -04:00
henk717 fe64e480ee
Merge pull request #171 from ebolam/united
Add Download Model Status
2022-07-26 00:52:12 +02:00
Henk 317e85dbaa New spacing language 2022-07-26 00:49:54 +02:00
henk717 c43fefed74
Merge branch 'KoboldAI:main' into united 2022-07-26 00:45:53 +02:00
Henk 2cf6b60c6f New updater backport 2022-07-26 00:45:40 +02:00
henk717 7721b72184
Merge branch 'KoboldAI:main' into united 2022-07-26 00:42:35 +02:00
Henk 4d8a633351 Aetherroom instead of aidg.club 2022-07-26 00:41:51 +02:00
ebolam 3b5ab92a02 Merge branch 'united' of https://github.com/ebolam/KoboldAI into united 2022-07-25 18:29:27 -04:00
ebolam 12acb50ee0 Fix for getting "model download status" when downloading config to figure out layer counts 2022-07-25 18:29:14 -04:00
henk717 46231519af
Merge pull request #172 from scott-ca/united
Added functionality to load all of the CLI arguments via a single JSON file
2022-07-26 00:14:46 +02:00
scott-ca ce2efa0149
Update customsettings_template.json 2022-07-23 22:06:56 -06:00
scott-ca 9dc9966433 Added functionality to add any/all args via json 2022-07-23 22:02:03 -06:00
ebolam 0ab3612e49
Merge branch 'henk717:united' into united 2022-07-22 13:58:58 -04:00
ebolam 907cf74b13 Added status bar for downloading models 2022-07-22 13:58:20 -04:00