rixty/KoboldAI-Client
1
1
Fork 0
mirror of https://github.com/KoboldAI/KoboldAI-Client.git synced 2025-06-05 21:59:24 +02:00
Code Issues Projects Releases Wiki Activity
3,004 Commits 1 Branch 5 Tags
cc593b4f910ab37732400fad34024b23905c9418
Commit Graph

1254 Commits

Author SHA1 Message Date
ebolam
022b729cd9 Fix for dynamic world info not properly disabling 
Fix for world info drag (still can't select text)
 2022-10-14 10:50:56 -04:00
ebolam
61774bffaa Fix for "blinking" world info cards 2022-10-13 12:21:49 -04:00
ebolam
fbc7a3ff3d Chat mode cleanup 2022-10-13 10:46:42 -04:00
ebolam
b5b08c78d0 Minor cleanup, better logging, debug on chat mode 2022-10-13 08:07:16 -04:00
Llama
8357c3e485 Merge branch 'united' into feature/anote-kwarg 2022-10-12 23:37:45 -07:00
Llama
4a01f345de Add include_anote kwarg to lua_compute_context. 
Add an optional keyword argument to lua_compute_context to control
whether the author's note should be included in the context.  The
default value is true, so if the include_anote kwarg is not specified
then the author's note will be included, which was the default
behavior prior to this change.

Also update the Lua API documentation to describe this kwarg.
 2022-10-12 23:18:19 -07:00
ebolam
36230e6804 Original UI Token streaming fixed 2022-10-12 14:26:07 -04:00
ebolam
ac1687195c Fix for visual bug on Chrome 2022-10-12 14:10:25 -04:00
ebolam
04689df322 Token Streaming Fixes for UI1 2022-10-12 12:48:34 -04:00
Henk
64715b18d6 Version bump 2022-10-12 14:54:11 +02:00
ebolam
56d8138e93 Welcome fix for original ui 2022-10-11 20:56:00 -04:00
ebolam
eebd03483b Welcome text v1 and slight mod to tooltip border 2022-10-11 20:45:09 -04:00
Henk
d5143eeb80 LUA Error as Error 2022-10-12 01:23:00 +02:00
onesome
2af27323fc More work on substitutions 2022-10-10 18:05:42 -05:00
somebody
0174b96ec1 Fix requesting a lower batch count than numseqs 2022-10-08 13:13:03 -05:00
ebolam
3f309c390f fix for world info box resizing 2022-10-07 18:52:44 -04:00
ebolam
140d3546df Fix for missing prompt on prompt only story load 2022-10-07 15:46:01 -04:00
ebolam
dfb05968c9 Merge commit 'refs/pull/188/head' of https://github.com/ebolam/KoboldAI into UI2 2022-10-07 14:31:59 -04:00
ebolam
3f21034704 Colab debug for 20B model error 2022-10-07 14:28:44 -04:00
ebolam
899c47b38c Fix for auto-save 2022-10-07 14:03:23 -04:00
ebolam
52b521dde7 Context viewer update 
Context bar update
in AI class update
 2022-10-07 09:30:33 -04:00
ebolam
abac61e41a Fix for scroll 2022-10-06 19:22:33 -04:00
ebolam
a41372cb79 Potential fix for scrolling 2022-10-05 15:24:55 -04:00
ebolam
265152c515 Fix for world info highlighting 2022-10-05 11:00:36 -04:00
ebolam
7f9c26332d Hopefully better infinity scroll 2022-10-05 09:41:29 -04:00
somebody
7746a43c96 Attention bias experiment 2022-10-03 21:30:17 -05:00
ebolam
b9c1ef7bfc Remove debug 2022-10-03 15:05:48 -04:00
ebolam
78fb4ba1e4 V1 story load streaming 2022-10-03 15:01:46 -04:00
ebolam
31760a19e1 Initial infinite scroll version 2022-10-03 14:21:01 -04:00
vfbd
bdfa6d86b7 Seed has to be a 64-bit unsigned int or PyTorch will throw an error 
tpu_mtj_backend's seed can be an integer of arbitrary size but we will
limit it to a 64-bit unsigned integer anyways for consistency.
 2022-10-02 17:50:32 -04:00
vfbd
dd1c25241d Allow sampler seed and full determinism to be read/written in /config 2022-10-02 17:43:54 -04:00
vfbd
1a59a4acea Allow changing sampler seed and sampler order from API 2022-10-02 16:25:51 -04:00
ebolam
d041da4ec6 Fix for new story bug 2022-10-01 14:12:32 -04:00
ebolam
f3b55fdfed Fix for V1 story loads 2022-09-30 16:32:37 -04:00
ebolam
2f35264153 Added flask-compress to speed up initial page load time 
Added check for tokenizer not being loaded early enough and crashing javascript (not needed until user interaction)
Removed unneeded CSS and JS files from web page load
 2022-09-30 15:20:34 -04:00
ebolam
bf58542ca5 Fix for story loading from V1 only pulling in first action 
Added accessibility labels for better support with screen readers.
 2022-09-30 14:05:28 -04:00
scythe000
a482ec16d8 Update aiserver.py - typo fix 
Changed 'beakmodel' to 'breakmodel' in the example comment.
 2022-09-30 10:29:32 -07:00
ebolam
efff4fb1a8 Fix for large UI1 story loads 2022-09-30 13:07:52 -04:00
ebolam
1e9be02770 Additional speed improvements 2022-09-30 08:34:37 -04:00
ebolam
6235be272e More optimizations 2022-09-29 20:31:40 -04:00
Divided by Zer0
90022d05c8 fix endpoint for get_cluster_models 2022-09-30 00:26:55 +02:00
ebolam
096b61962c Fix for load time. 
Need world info loading testing as may have regression
 2022-09-29 14:41:28 -04:00
ebolam
51b8b1d223 Partial fix for text context 2022-09-29 12:12:46 -04:00
ebolam
475d4bc48c Debugging large story import 2022-09-29 08:12:15 -04:00
vfbd
6758d5b538 Merge branch 'united' into mkultra 2022-09-28 14:30:34 -04:00
ebolam
c28ad27c1d Merge commit 'refs/pull/181/head' of https://github.com/ebolam/KoboldAI into UI2 2022-09-28 12:59:53 -04:00
ebolam
e7973e13ac Fix for GPT models downloading even when present in model folder 2022-09-28 12:47:50 -04:00
ebolam
72fc68c6e4 Fix for lazy loading on models after a non-lazy load model 2022-09-27 19:52:35 -04:00
ebolam
4aa842eada Merge commit 'refs/pull/180/head' of https://github.com/ebolam/KoboldAI into united 2022-09-27 19:29:05 -04:00
ebolam
be719a7e5e Fix for loading models that don't support breakmodel (GPU/CPU support in UI) 2022-09-27 19:02:37 -04:00