Commit Graph

765 Commits

Author SHA1 Message Date
henk717 ecd7b328ec Further Polishing
Multiple smaller changes to get 1.17 in shape for its release.
2022-02-01 11:15:44 +01:00
henk717 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
henk717 90fd67fd16 Update aiserver.py 2022-01-31 19:06:02 +01:00
henk717 b69e3f86e1 Update aiserver.py
Removes a debug line
2022-01-31 18:57:47 +01:00
henk717 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
henk717 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
henk717 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
henk717 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
henk717 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
henk717 ddfa21e6dd Breakmodel Fixes
Multiple old references and one mistake in my last commit fixed
2022-01-30 17:40:43 +01:00
henk717 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
henk717 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
henk717 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
henk717 fca7f8659f Badwords unification
TPU's no longer use hardcoded badwords but instead use the var
2022-01-29 18:09:53 +01:00
henk717 4a4fa4ca29 Update readme.md 2022-01-29 12:45:15 +01:00
henk717 f9f25c01e4 HTML escape the last commit
</s> didn't work, needed to be HTML escaped (Thanks for the tip VE!)
2022-01-28 19:21:05 +01:00
henk717 be0e57185f Improved Model Support
Changed the model VRAM requirements to what you'd need to comfortably run the model rather than barely (Like with the manual). Will probably revise this in a later commit.

More importantly, it now supports models that use </s> which will be required to support XGLM and Fairseq models.
2022-01-28 18:03:30 +01:00
henk717 9356573ac9 Merge branch 'united' of https://github.com/henk717/KoboldAI into united 2022-01-25 06:39:54 +01:00
henk717 987e78f980 More loading fixes
My last attempt at fixing this caused GPT2 to break, since the other fix is an edge case we assume that the GPT2 method should be used, and if that fails we try the other one to catch rare errors with bad model config's.
2022-01-25 06:39:23 +01:00
henk717 2d7f39247d TPU descriptions 2022-01-25 06:22:32 +01:00
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
henk717 392c59d48b
Merge pull request #72 from VE-FORBRYDERNE/rep-pen
Repetition penalty slope and range
2022-01-25 05:39:09 +01:00
Gnome Ann 3f18888eec Repetition penalty slope and range 2022-01-24 15:30:38 -05:00
henk717 85cb6342e2 Fix C1 2022-01-24 07:08:28 +01:00
henk717 e69265cb4f Logits Viewer
Logits Viewer by VE
2022-01-23 01:09:41 +01:00
henk717 91077938c8 Update index.html 2022-01-23 01:06:52 +01:00
henk717 0846d57368 0.17 polish 2022-01-23 01:05:09 +01:00
henk717 f9a34951cf
Merge pull request #71 from jojorne/patch-1
Display the options text as A.I. writes it
2022-01-22 23:24:45 +01:00
henk717 c9999b6388
Merge pull request #70 from VE-FORBRYDERNE/patch
Don't throw an error in `update_story_chunk` if you try to edit a nonexistent chunk
2022-01-22 23:24:34 +01:00
henk717 4e7440804c
Merge pull request #69 from VE-FORBRYDERNE/lua
Lua compatibility enhancements
2022-01-22 23:23:47 +01:00
henk717 f79db7059a Fall back to old json load
Turns out model_config does not work on models that have no model_type defined. In case this happens we now fall back to the old .json loading method. This will not work in --colab mode if its not already a local model, but since almost all modern models define a model type and to my knowledge all models on huggingface do that should not be an issue. If it is we can always ask the model creator to either update it, distribute the model differently or load that model with --remote instead of --colab.
2022-01-22 23:21:19 +01:00
jojorne 47dbddff78
Display the options text as A.I. writes it
When using `Gens Per Action`, display the options text as A.I. writes it. White space are preserved and break lines as necessary.
2022-01-22 17:10:35 -03:00
Gnome Ann bf2b02d366 Don't error in `update_story_chunk` if chunk index doesn't exist 2022-01-21 21:19:32 -05:00
Gnome Ann fab0913270 Call `setgamesaved(False)` in `update_story_chunk` and `remove_story_chunk` 2022-01-21 16:39:51 -05:00
henk717 9cddaa8041 Official branch is now default 2022-01-21 11:23:37 +01:00
henk717 8e00c4a190 KoboldAI launcher for Jupyter Notebook platforms 2022-01-21 11:21:24 +01:00
henk717 67ea081033 Link Fix 2022-01-21 11:12:43 +01:00
henk717 17f284b837 Descriptions 2022-01-21 11:10:44 +01:00
Gnome Ann 82455e310b Modify Lua `warn()` function to support `@on` and `@off` 2022-01-21 01:28:26 -05:00
Gnome Ann 44d49ed0b2 Lua `require` function will now display errors properly 2022-01-21 00:56:25 -05:00
henk717 d209c2f7ac
Merge pull request #68 from VE-FORBRYDERNE/patch
Sync memory properly after random game request
2022-01-21 00:48:57 +01:00
Gnome Ann 72a7aac2c7 Sync memory properly after random game request 2022-01-20 15:14:55 -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
henk717 1c98bf4f63
Merge pull request #67 from ebolam/united
Autosave
2022-01-20 14:03:41 +01:00
ebolam dffd00265b Added autosave feature. When action is submitted it will save if the save setting is on and if the filename is set. 2022-01-20 07:46:34 -05:00
henk717 b54d66c522 Predefined Settings 2022-01-20 13:44:04 +01:00
henk717 9564ac1892 Adds GPT-Neo-2.7B-AID 2022-01-20 11:22:20 +01:00
henk717 13c54b1a89 Seperate Google Drive folders to its own section
This allows Colab developers to first get the correct folder structure on drive, before placing a configuration file for the model. That way we can quickly add the settings for a model without maintaining the init settings in two different lines. Its a substitute to the common --init only and --init skip approach from before.
2022-01-20 11:17:01 +01:00
henk717 9532b56cb8 Universal Model Settings
No longer depends on a local config file enabling the configuration to work in --colab mode.
2022-01-20 10:11:11 +01:00
henk717 c25e2a33f1
Merge pull request #66 from VE-FORBRYDERNE/patch
Set eventlet threadpool size back to 1
2022-01-20 08:31:53 +01:00