LightSaveUs
cd46b28813
Slight Tooltips Refining
2022-10-28 23:01:08 +03:00
LightSaveUs
49795525a7
Additional Tooltips Changes
2022-10-28 03:09:13 +03:00
LightSaveUs
58fe6c332f
KoboldAI Mode -> Game Mode
2022-10-27 17:51:27 +03:00
LightSaveUs
e6af759f87
Add Prompt -> Stored Prompt
2022-10-27 17:48:00 +03:00
LightSaveUs
4a230157c1
Additional Refining
2022-10-27 17:40:24 +03:00
LightSaveUs
dbe6ac3990
Tooltips Refining
2022-10-27 17:14:08 +03:00
ebolam
147b9be9e5
Add no double space option
2022-10-26 20:53:47 -04:00
ebolam
7579137433
Add automatic hide of the World Info Depth setting when using the alternative text generation method (alt gen ignores World Info Depth)
2022-10-24 14:22:18 -04:00
ebolam
dffbd63f46
Start of WI card text select fix_text
2022-10-14 11:33:13 -04:00
ebolam
9bef5c1f90
Moved experimental features to a backend variable
2022-10-13 14:16:02 -04:00
LightSaveUs
3e3118b907
Model in memory -> Model in Memory
2022-10-06 06:11:39 +03:00
ebolam
c90d157b7d
Spelling fix
2022-09-20 18:43:25 -04:00
ebolam
8dfe0eba8a
Better Image Generation
2022-09-20 14:49:18 -04:00
ebolam
335f12c415
Better image generation
2022-09-20 12:01:18 -04:00
ebolam
b700d5e86e
Chat and Adventure mode Fix
2022-09-07 10:27:05 -04:00
ebolam
bbb7060474
Added beep option to beep on completion
2022-09-02 12:33:25 -04:00
ebolam
e9678ceea3
Merge commit 'refs/pull/82/head' of https://github.com/ebolam/KoboldAI into UI2
2022-08-30 14:50:28 -04:00
LightSaveUs
a88452e17e
Fixed AN Depth values range
2022-08-29 18:11:42 +03:00
LightSaveUs
24594160d2
Renamed "Insert Depth" to "AN Depth"
2022-08-26 05:33:13 +03:00
ebolam
aa2dc61ad0
Moved token bar
2022-08-24 13:50:09 -04:00
ebolam
e0cce3d082
W++ Commit. Data can be synced (not used yet, needs formatting)
2022-08-22 20:52:45 -04:00
ebolam
34ed679ab9
Tooltip Fixes
2022-08-22 18:51:45 -04:00
somebody
95796faf41
Add show budget setting
2022-08-22 17:25:55 -05:00
ebolam
d9737f83eb
More Tooltip Text Changes
2022-08-22 18:19:13 -04:00
ebolam
2187ef2d9e
Setting Text Changes
2022-08-22 18:07:03 -04:00
ebolam
7ec192117f
Format option implemented in UI2
2022-08-22 11:51:10 -04:00
ebolam
fdcf463c76
Added alt text gen
2022-08-18 12:58:24 -04:00
ebolam
1140c56925
Probabilities are now in the action list properly. Need to add proper transmits to client
2022-08-17 20:19:23 -04:00
ebolam
91ab8ca3ce
Merge remote-tracking branch 'remotes/origin/vars-rename' into UI2
2022-08-17 10:26:06 -04:00
ebolam
e164af9264
Sampler Order added to UI
2022-08-12 21:18:31 -04:00
ebolam
7f4dbdd977
Checkin
2022-08-07 14:00:06 -04:00
Henk
0a0bd75617
Polish
2022-08-06 16:42:15 +02:00
ebolam
2ee4371622
Implemented token streaming from one-some
2022-08-05 12:35:38 -04:00
somebody
f6d046fe1b
Add token probability visualizer
2022-08-04 13:49:37 -05:00
ebolam
3e256a627e
Fix for autosave
2022-08-04 09:58:38 -04:00
somebody
a4d81292f8
Add token streaming option
2022-07-27 22:13:08 -05:00
Henk
317e85dbaa
New spacing language
2022-07-26 00:49:54 +02:00
ebolam
796a1dcf16
CSS change to move options to below game text for mobile
2022-07-05 14:11:05 -04:00
henk717
fd44f0ded3
Merge branch 'KoboldAI:main' into united
2022-07-03 15:12:12 +02:00
Henk
d041ec0921
Safer defaults and more flexibility
...
There have been a lot of reports from newer users who experience AI breakdown because not all models properly handle 2048 max tokens. 1024 is the only value that all models support and was the original value KoboldAI used. This commit reverts the decision to increase this to 2048, any existing configurations are not effected. Users who wish to increase the max tokens can do so themselves. Most models handle up to 1900 well (The GPT2 models are excluded), for many you can go all the way. (It is currently not yet known why some finetunes cause a decrease in maxtoken support,
In addition this commit contains a request for more consistent slider behavior, allowing the sliders to be changed at 0.01 intervals instead of some sliders being capped to 0.05.
2022-07-03 15:07:54 +02:00
vfbd
048bd0ff3b
Add support for setting the RNG seed and full determinism
2022-06-28 13:21:05 -04:00
ebolam
b906742f61
Working options.
2022-06-26 16:36:07 -04:00
ebolam
b0ac4581de
UI v2 Initial Commit
2022-06-22 18:39:09 -04:00
fdb2a7fa4c
Top-A sampling
2022-06-10 22:28:20 -04:00
20e48b11d7
Typical sampling
2022-03-27 16:25:50 -04:00
ebolam
b0f1bdf2fd
Merge branch 'henk717:united' into united
2022-01-26 11:27:12 -05:00
henk717
2bb263c65d
Reordering Settings
...
More settings reordering so similar settings are on the same rows now that we have more settings for the repetition penalty. Amount to generate is now top left so some muscle memory may be lost with the temp. But the settings that control AI randomness are on the same row now, and repetition related settings are next to each other as well.
2022-01-25 06:10:39 +01:00
3f18888eec
Repetition penalty slope and range
2022-01-24 15:30:38 -05:00
ebolam
bd0732fbd6
Fix for redo with options.
...
Added debug menu
2022-01-24 12:54:44 -05:00
henk717
f578dd1782
Setting Toggles Reordering
...
Bit more alphabetical and a (in my eyes) more logical order of the settings.
2022-01-20 19:23:23 +01:00
