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
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
LightSaveUs
9c2fde91e4
TPU Formatting Fix
...
Removed the information about irrelevant style (Chatbot)
2022-07-22 13:28:32 +03:00
LightSaveUs
4bd3b53c0a
GPU Formatting Fix
...
Removed the information about irrelevant style (Chatbot)
2022-07-22 13:27:57 +03:00
LightSaveUs
1eecef8c8b
GPU Formatting Fix #2
...
Deleted information about removed Convo and C1 chatbot models.
2022-07-22 13:15:08 +03:00
LightSaveUs
bd69cccefc
GPU Formatting Fix
...
Formatting issues fixes and unification
2022-07-21 03:10:14 +03:00
LightSaveUs
97ff194261
TPU Formatting Fix
...
Minor code cleanup, formatting issues fixes and unification
2022-07-21 02:52:20 +03:00
henk717
025db3bd04
Merge pull request #138 from VE-FORBRYDERNE/lazy-loader
...
Fix for lazy loader in PyTorch 1.12
2022-07-12 23:02:58 +02:00
henk717
836759d826
Merge pull request #137 from VE-FORBRYDERNE/jaxlib
...
TPU Colab hotfix
2022-07-12 23:02:40 +02:00
vfbd
39d48495ce
Fix for lazy loader in PyTorch 1.12
...
There is no `torch._StorageBase` in PyTorch 1.12, but otherwise it still
works.
2022-07-12 16:48:01 -04:00
vfbd
70aa182671
Restrict jaxlib version in TPU Colabs
2022-07-12 16:30:26 -04:00
henk717
dd6da50e58
Merge pull request #136 from VE-FORBRYDERNE/opt
...
Fix base OPT-125M and finetuned OPT models in Colab TPU instances
2022-07-05 21:35:39 +02:00
vfbd
2a78b66932
Fix base OPT-125M and finetuned OPT models in Colab TPU instances
2022-07-05 15:28:58 -04:00
vfbd
c94f875608
Fix Z algorithm in basic phrase bias script
2022-07-05 14:43:58 -04:00
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
Henk
e2f7fed99f
Don't turn gamestarted off
2022-07-02 12:59:14 +02:00
henk717
90c5cebb6d
Merge pull request #134 from VE-FORBRYDERNE/editor
...
Editor fixes
2022-07-01 20:32:18 +02:00
vfbd
c336a43544
Fix some remaining editor whitespace-fixing issues
2022-07-01 13:45:57 -04:00
vfbd
c3eade8046
Fix editor bug in iOS when adding newline at end of the last action
...
Not only does iOS also have that issue that Chromium-based browsers
have, but it also has a different issue where it selects all text in the
last chunk of your story, so I added some code to deselect the text in
that case.
2022-07-01 13:12:57 -04:00
vfbd
1ff0a4b9a9
Submit button now waits for inlineedit/inlinedelete commands
2022-06-30 12:23:06 -04:00
vfbd
cccf8296fc
Fix enter key sometimes putting two newlines in editor
...
This happens when, in a Chromium-based browser, you try to insert a
newline at the end of the last action of your story.
2022-06-30 12:03:39 -04:00
vfbd
ce5f4d3dda
Click on blank part of editor to defocus in Chromium based browsers
...
In Chromium based browsers you can now click the blank part of the
editor to submit changes. This is to maintain consistency with the
editor behaviour in Firefox which already did this when you clicked on
the blank part of the editor.
2022-06-30 11:31:54 -04:00
vfbd
accbaea991
Fix a problem where a story with only the prompt cannot be edited
2022-06-30 11:08:22 -04:00
henk717
856e8d5c86
Merge pull request #133 from VE-FORBRYDERNE/whitespace
...
Fix the cleanupChunkWhitespace function
2022-06-28 18:22:24 +02:00
vfbd
d55b4d9bbc
Fix the cleanupChunkWhitespace function
2022-06-28 12:18:57 -04:00
henk717
ad9ec6eaba
Merge pull request #132 from VE-FORBRYDERNE/whitespace-cleanup
...
Story whitespace cleanup backport
2022-06-26 20:35:50 +02:00
vfbd
6576f5c01d
Make sure editor changes are applied before submitting
...
(cherry picked from commit ae41ad298c
2022-06-26 14:06:57 -04:00
vfbd
ebba79fed6
Remove trailing whitespace from submissions
...
(cherry picked from commit b99d1449c9
2022-06-26 14:06:34 -04:00
vfbd
6ba7429eea
Don't add sentence spacing if submission is empty
...
When you retry, it actually sends an empty submission, so if you have
add sentence spacing on, retrying could add an extra action with a
single space.
(cherry picked from commit 151407a001
2022-06-26 14:06:18 -04:00
vfbd
9d09ae5fea
Clean up whitespace in the editor as well
...
(cherry picked from commit 6e138db1c0
2022-06-26 14:05:04 -04:00
vfbd
2a4d37ce60
Clean up whitespace at the end of actions when loading story
...
Specifically, we merge blank actions into the next action and we move
whitespace at the end of non-blank actions to the beginning of the next
action.
(cherry picked from commit 4b16600e49
2022-06-26 14:04:36 -04:00
vfbd
e30abd209f
Preserve whitespace in the editor
...
(cherry picked from commit 793d788706
2022-06-26 14:04:16 -04:00
Henk
9e7eb80db4
Nerys V2 part 2
2022-06-25 14:03:19 +02:00
Henk
ecc6ee9474
Nerys V2
2022-06-25 13:47:49 +02:00
henk717
a2d2ea0735
Typo Fix
2022-06-25 13:14:27 +02:00
henk717
2495b9380d
Nerys V2
2022-06-25 13:08:30 +02:00
Henk
8be0964427
AIDG Import Fix
2022-06-24 18:29:06 +02:00
henk717
27e16aecf2
Model Cleaner (suggested by Shrinkarom)
2022-06-24 14:03:58 +02:00
henk717
c3af92e9af
Koboldai.org | New NeoX | Cloudflare
2022-06-24 10:43:06 +02:00
henk717
ec0bc1cc17
Merge pull request #130 from VE-FORBRYDERNE/neox-badwords
...
GPT-NeoX HF model badwords fix
2022-06-23 21:05:42 +02:00
vfbd
3da885d408
GPT-NeoX HF model badwords fix
2022-06-23 15:02:43 -04:00
henk717
d94f29a68a
Merge pull request #127 from VE-FORBRYDERNE/tracer
...
Fix JAX UnexpectedTracerError
2022-06-23 19:29:51 +02:00
henk717
1d41966d88
Merge pull request #129 from VE-FORBRYDERNE/budget
...
Account for lnheader in budget calculation
2022-06-23 12:39:20 +02:00
vfbd
0eb9f8a879
Account for lnheader in budget calculation
2022-06-22 19:16:24 -04:00
henk717
5f9a116052
Merge pull request #128 from VE-FORBRYDERNE/neox
...
TPU support for HF GPT-NeoX model
2022-06-22 01:39:53 +02:00
8c594c6869
Correct the padding token for GPT-NeoX
2022-06-21 19:37:43 -04:00
a7f667c34c
Use NeoX badwords when loading from HF GPT-NeoX model
2022-06-21 19:33:25 -04:00
5e3c7c07ae
Merge branch 'main' into neox
2022-06-21 19:30:51 -04:00
