ec54bc9d9b
Fix typo in send_debug()
2022-02-12 20:11:35 -05:00
f682c1229a
Fix fairseq newline handling issues
2022-02-12 13:23:59 -05:00
c1af8f72c3
Merge pull request #75 from ebolam/united
...
Fixed retry bug due to redo/pin code
2022-02-11 03:27:51 +01:00
633152ee84
Fixed Retry bug due to redo/pin code
2022-02-10 10:01:07 -05:00
cd00373cfb
Deleted unused svg
2022-02-10 09:21:07 -05:00
e1ef4e4fa8
Merge pull request #74 from ebolam/united
...
Redo, Pinning, and docker enhancements
2022-02-07 01:06:36 +01:00
c0bbe9f810
Reverted docker-cuda to mainline version.
2022-02-06 19:04:13 -05:00
586b989582
Redo bug fix
2022-02-06 18:53:24 -05:00
98609a8abc
Merge branch 'united' of https://github.com/ebolam/KoboldAI into united
2022-02-06 13:48:34 -05:00
80ae054cb5
Merge branch 'henk717:united' into united
2022-02-06 13:42:59 -05:00
9e17ea9636
Fixed model downloading problem where models were downloaded multiple times
2022-02-06 13:42:46 -05:00
8195360fcc
Merge branch 'united' of https://github.com/ebolam/KoboldAI into united
2022-02-06 12:31:45 -05:00
7695eeb31a
Merge branch 'KoboldAI:main' into united
2022-02-06 18:06:07 +01:00
c38108d818
Merge pull request #73 from VE-FORBRYDERNE/xglm-breakmodel
...
Breakmodel support for the fairseq models
2022-02-06 18:05:59 +01:00
223af82083
GPU Link Fix
2022-02-06 12:05:00 +01:00
03e017bffd
Release of 1.17
...
Release of 1.17
2022-02-06 11:59:58 +01:00
040455b100
Enable Colab Mode in Colab
...
Now that we are ready to upstream we can safely enable the intended colab mode without breaking the old version.
2022-02-06 11:52:55 +01:00
475995f8a5
Merge branch 'henk717:united' into united
2022-02-04 10:21:10 -05:00
91f3f25f4d
Update readme.md
2022-02-04 01:00:26 +01:00
5534fc9800
Moved build script into the docker folder
2022-02-03 08:25:51 -05:00
02c7ca3e84
Merge branch 'henk717:united' into united
2022-02-03 08:11:06 -05:00
0684a221cd
Changed pin icon for re-dos to be a circular arrow that is not clickable to make it clear it is a redo action and cannot be cleared.
2022-02-03 08:08:43 -05:00
3ee63b28c5
Defaults and Downloads
...
Default settings for the new repetition penalty settings (Better suggestions very much welcome since broader community testing has not been done).
Updated the Readme with the link to the offline installer.
2022-02-03 13:13:26 +01:00
4904af6adc
Fix a mistake in the previous commit
2022-02-02 23:04:59 -05:00
78f52063c7
Fix XGLM soft prompts
2022-02-02 22:45:16 -05:00
3a6d8f1030
Added script to build the 5 images for the docker containers
2022-02-02 15:18:18 -05:00
004bb3bcc8
change tag name
2022-02-02 15:15:11 -05:00
6f7578abca
adding base environment file
2022-02-02 15:10:50 -05:00
604246d12c
Merge branch 'henk717-united' into united
2022-02-02 15:05:14 -05:00
e2d2ebcae6
upstream merge
2022-02-02 15:04:59 -05:00
d847d04605
Fix some typos in XGLM breakmodel
2022-02-01 16:00:46 -05:00
8e1169ea61
Enable vars.bmsupported when using XGLM
2022-02-01 15:31:59 -05:00
e7f65cee09
XGLM breakmodel
2022-02-01 13:04:35 -05:00
c14e6fe5d2
Revert parralism
...
Testing is done, seems to cause issues in the order things happen with the interface.
2022-02-01 18:58:48 +01:00
d68a91ecd3
Save model values
...
Without saving these they get lost after someone saves. So saving them is more important than the model being able to override them after the fact.
2022-02-01 18:37:52 +01:00
b8e08cdd63
Enable Tokenizer Parralism
...
Has proven to be safe in my internal testing and does help with the interface lag at boot.
Enabling this so it can get wider testing.
2022-02-01 12:00:53 +01:00
ecd7b328ec
Further Polishing
...
Multiple smaller changes to get 1.17 in shape for its release.
2022-02-01 11:15:44 +01:00
36b6dcb641
Increase newlinemode compatibility
...
Ran into issues with other modes like chatmode and adventure, moved it further down the pipeline and converting </s> back to \n before processing additional formatting.
Still has an issue with the html formatting not working, but at least the AI works now.
2022-01-31 19:39:32 +01:00
90fd67fd16
Update aiserver.py
2022-01-31 19:06:02 +01:00
b69e3f86e1
Update aiserver.py
...
Removes a debug line
2022-01-31 18:57:47 +01:00
8466068267
Don't save newlinemode
...
On second thought, it is probably better to not save this. Advanced users can add this themselves and that way newer versions of the model can override it if redownloaded.
2022-01-31 18:41:23 +01:00
729be62821
</s> new line mode
...
Needed for Fairseq and XGLM models that do not understand the regular \n .
2022-01-31 18:39:34 +01:00
44d49ea732
Remove Huggingface Repo
...
Huggingface's repo is further behind than conda-forge so we will no longer offer it in the installer. The more is loaded from conda-forge the better. The same transformers package will still be installed, but a newer one from conda-forge is now guaranteed.
2022-01-31 16:21:10 +01:00
03433810f1
KML improvements
...
Don't parse > since that has a different meaning for us, also whitelisting a few more markdown tags so lists work.
2022-01-30 20:07:47 +01:00
a484244392
Welcome Message API
...
Allows model creators to customize the welcome message using Markdown and Limited HTML
Existing United users need to run install_requirements..bat again, you can leave the existing dependencies intact.
2022-01-30 19:47:30 +01:00
ddfa21e6dd
Breakmodel Fixes
...
Multiple old references and one mistake in my last commit fixed
2022-01-30 17:40:43 +01:00
57344935f6
--model without breakmodel disables bmsupported
...
Last commit it only did a warning, now it will turn bmsupported off so that the GPU routine is used.
2022-01-30 17:16:35 +01:00
f0c0a990ea
NoBreakmodel variable
...
Adds a Nobreakmodel var that allows Breakmodel to be turned off. This can be done trough commandline or a model config (In case Neo is used by the models config without it being a true Neo model that is compatible with breakmodel).
In addition I removed the args.colab check for breakmodel support and instead make args.colab activate nobreakmodel. And I have added a new check so that breakmodel is not even attempted if you do not specify the layers but do launch a model from the command line.
2022-01-30 17:06:15 +01:00
5b5a479f29
Threading + Memory Sizes
...
Polish effort to suppress a warning and list more accurate VRAM as tested with the full 2048 max tokens.
2022-01-30 13:56:25 +01:00
fca7f8659f
Badwords unification
...
TPU's no longer use hardcoded badwords but instead use the var
2022-01-29 18:09:53 +01:00
