somebody
56bcd32f6d
Model: Fix ReadOnly
...
whoops
2023-02-26 12:40:20 -06:00
somebody
a73804ca1e
Accelerate: Remove HAS_ACCELERATE
...
Accelerate has been a dependency for a while, and as such we probably
shouldn't be lugging around code that assumes it isn't present.
2023-02-26 12:18:06 -06:00
somebody
5e3b0062ee
Model: Tokenizer fix
2023-02-26 12:17:49 -06:00
somebody
8d49b5cce1
Model: More TPU stuff
2023-02-26 12:09:26 -06:00
somebody
d53d2bcc45
Model: Fix crash on full GPU load
2023-02-25 18:19:46 -06:00
somebody
465e22fa5c
Model Fix bugs and introduce hack for visualization
...
Hopefully I remove that attrocity before the PR
2023-02-25 18:12:49 -06:00
somebody
ffe4f25349
Model: Work on stoppers and stuff
2023-02-25 17:12:16 -06:00
somebody
6b4905de30
Model: Port rest of models over
...
Generation's still broke but it's a start
2023-02-25 16:05:56 -06:00
somebody
f8c4158ebc
Model: Successful load implementation
...
The goal of this series of commits is to have an implementation-agnostic
interface for models, thus being less reliant on HF Transformers for model
support. A model object will have a method for generation, a list of callbacks
to be run on every token generation, a list of samplers that will modify
probabilities, etc. Basically anything HF can do should be easily
implementable with the new interface :^)
Currently I've tested the loading of pre-downloaded models with
breakmodel between GPUs and that works, though essentially no testing
has been done in the larger scheme of things. Currently this is about
the only supported configuration, and generation isn't very functional.
2023-02-24 21:41:44 -06:00
henk717
0e7b2c1ba1
Merge pull request #293 from jojorne/jojorne-patch-save-load-story-with-UTF-8-encoding
...
Save/Load Story with UTF-8 encoding.
2023-02-22 19:59:33 +01:00
jojorne
d3bedfcbda
Include koboldai_vars.save_story().
2023-02-22 15:42:56 -03:00
jojorne
d6c9f5f1f5
Save/Load Story with UTF-8 encoding.
2023-02-22 14:40:42 -03:00
henk717
72135f7156
Merge pull request #292 from YellowRoseCx/united
...
updates PyTorch to allow AMD gpu splitting
2023-02-21 01:52:46 +01:00
YellowRoseCx
83bd1f0db6
updates PyTorch to allow AMD gpu splitting
...
Feature adding update for AMD GPUs:
Changes the installed PyTorch version from 1.12.1+rocm5.1.1 to the newer stable version 1.13.1+rocm5.2 to allow AMD GPUs to utilize VRAM splitting across multiple GPUs
2023-02-20 18:40:21 -06:00
Henk
b3083034ea
UI2 Botname
2023-02-19 17:12:14 +01:00
Henk
9e6a5db745
UI1 Botname
2023-02-19 16:22:26 +01:00
henk717
93f313d6e3
Merge pull request #291 from pi6am/fix/save-as
...
Fix an exception using Save As from the classic UI
2023-02-19 13:21:10 +01:00
Llama
117f0659c3
Fix exception using Save As from the classic UI
...
The `saveas` method was modified to take a data dict but one of the
else blocks still referred to the previous `name` parameter. Assign
to `name` to fix the `NameError: name 'name' is not defined` exception.
2023-02-18 23:41:17 -08:00
Henk
cd566caf20
Revision Fixes (Removes the workaround)
2023-02-19 00:51:50 +01:00
henk717
886153f0b7
Merge pull request #286 from YellowRoseCx/united
...
Added tooltip to WI noun section - fixed file location
2023-02-18 19:05:41 +01:00
henk717
3358d1dc53
Merge pull request #289 from jojorne/jojorne-patch-keep-genseqs-visible-on-submit-memory
...
Don't hide genseqs on submit memory
2023-02-18 19:01:33 +01:00
Henk
aa6ce9088b
Fix vscode artifacting
2023-02-18 18:47:15 +01:00
Henk
a9a724e38c
Merge branch 'main' into united
2023-02-18 18:14:03 +01:00
YellowRoseCx
7daa927fbb
Merge branch 'henk717:united' into united
2023-02-17 15:57:15 -06:00
jojorne
150d0ea695
Don't hide genseqs on submit memory.
2023-02-17 05:49:07 -03:00
Llama
54dd4abeb8
Merge pull request #19 from henk717/united
...
Merge united
2023-02-17 00:27:44 -08:00
Henk
e905f2db2d
More API stuff to User
2023-02-16 02:50:52 +01:00
Henk
f50f5b530a
Move OAI to User Settings
2023-02-16 02:48:20 +01:00
YellowRoseCx
00a8806e0d
Added tooltip to WI noun section
2023-02-13 20:36:41 -06:00
henk717
3752ad1c2e
Merge pull request #282 from ebolam/UI2
...
Fix for UI1 upload bug
2023-02-13 21:04:29 +01:00
ebolam
c8059ae07e
Fix for UI1 upload bug
2023-02-13 14:35:55 -05:00
Henk
ec3ed9b4d9
Don't save TQDM
2023-02-12 04:29:36 +01:00
henk717
d7cce6473a
Merge pull request #279 from ebolam/UI2
...
Chat mode stopper fix, Class Split Adjustments
2023-02-11 23:58:54 +01:00
henk717
5f108bdf98
Merge pull request #280 from SillyLossy/booleanforunited
...
Fix boolean API schemas name clash
2023-02-11 16:06:50 +01:00
--global
a680d2baa5
Fix boolean API schemas name clash
2023-02-11 15:11:35 +02:00
Henk
cc01ad730a
Don't install safetensors for MTJ
2023-02-11 11:20:21 +01:00
Henk
86ab741481
Don't install safetensors for MTJ
2023-02-11 11:17:15 +01:00
ebolam
89e98191a0
Class Split Fix
2023-02-10 16:30:45 -05:00
ebolam
426041f1cf
Class Fix
2023-02-10 16:22:37 -05:00
ebolam
606137f901
Class split fix for status bar
2023-02-10 16:17:03 -05:00
ebolam
d2ff58c2dd
Chat mode stopper modified to only stop, not trim output (using Henky's regex for that)
2023-02-10 16:10:23 -05:00
Henk
b58daa1ba1
Pin Flask-cloudflared
2023-02-10 19:11:13 +01:00
Henk
84452d1b11
Pin Flaskcloudflared
2023-02-10 19:01:07 +01:00
Henk
503e7e780e
Cleanup bridge on Colab (To prevent future bans)
2023-02-09 23:49:13 +01:00
Henk
cd63882299
Fix an invalid crash in the horde bridge
2023-02-09 23:40:09 +01:00
ebolam
4439e1d637
Chat Mode Stopper Test
2023-02-09 11:40:00 -05:00
ebolam
0487b271b8
Merge branch 'UI2' of https://github.com/ebolam/KoboldAI into UI2
2023-02-09 10:54:48 -05:00
ebolam
b29d4cef29
Add basic authentication option for webUI image generation
2023-02-09 10:54:38 -05:00
ebolam
709bd634b3
Merge pull request #365 from ebolam/chatmodestoppertest
...
Fix for chat mode stopper
2023-02-09 10:52:34 -05:00
Llama
2567a061ca
Merge pull request #18 from henk717/united
...
Merge united: Unblock themes
2023-02-05 00:06:46 -08:00
