rixty
/
KoboldAI-Client
mirror of https://github.com/KoboldAI/KoboldAI-Client.git
1
1
Fork 0
Code Issues Projects Releases Wiki Activity
632 Commits 1 Branch 5 Tags 120 MiB
Commit Graph

632 Commits

Author SHA1 Message Date
Gnome Ann 3e0b1a9e63 Fix scrolling problems with WI entries with long names/comments 2021-12-05 01:39:42 -05:00
Gnome Ann 08992dec7e Use a green horizontal line as the drag-and-drop placeholder 2021-12-05 00:34:44 -05:00
Gnome Ann b99ac92a52 WI folders and WI drag-and-drop 2021-12-04 23:59:28 -05:00
Gnome Ann d2d338d314 Improve TPU backend compilation times with `numseqs > 1` 
A Python `for` loop was replaced with a `jax.lax.scan` call so that JAX
only compiles the `transformer.generate_initial` function one time
instead of `numseqs` times. This is because JAX unrolls Python built-in
loops like `for`. The compilation times should now be about the same as
they were before the upgrade to JAX 0.2.21.
 2021-11-30 19:22:40 -05:00
Gnome Ann c1e7c1643f Fix unbound axis error in tpu_mtj_backend.py when `numseqs > 1` 2021-11-30 14:06:46 -05:00
Gnome Ann 3c349e6aaf Modify TPU backend code to support JAX 0.2.21 
The original one supported versions of JAX up to 0.2.12, and possibly also some
earlier versions. This new code supports exclusively JAX 0.2.21 and does not
work with any earlier or later versions of JAX. However, this new code benefits
from not needing to recompile when changing "Amount To Generate" and also from
supporting stopping generation early, which makes an implementation of Dynamic
World Info Scan finally possible.
 2021-11-30 10:13:02 -05:00
henk717 9e3318c696 Update colabkobold.sh 
Bugfix
 2021-11-29 18:42:40 +01:00
henk717 4244b588cb Ngrok requirements 
Adds ngrok to the requirements.txt files
 2021-11-29 18:13:30 +01:00
henk717 fd19e2bfd6 Allow Ngrok 
Adds --ngrok to the Colab script
 2021-11-29 18:12:45 +01:00
henk717 44d8068bab Ngrok Support 
Not recommended for home users due to DDoS risks, but might make Colab tunnels more reliable.
 2021-11-29 18:11:14 +01:00
henk717 eef675ce21
Further Streamlining Dependencies 
Hopefully this will make Kaggle work
 2021-11-29 16:43:45 +01:00
henk717 ff99e4c0e9
Merge branch 'KoboldAI:main' into united 2021-11-29 12:06:03 +01:00
henk717 d4a7ff5ccb Better Repetition Penalty Slider 
Allow users more control since 6B is sensitive
 2021-11-29 08:28:51 +01:00
henk717 f7993d5ef1
Merge pull request #84 from adcar/patch-1 
Fixed a small typo
 2021-11-28 17:58:40 +01:00
Alexander D. Cardosi 8d922d83a9
Fixed a small typo 2021-11-28 11:30:23 -05:00
henk717 6b9d744679
Torch needs to be newer 
Uncapping the version to see the effect (Testing on the git since Colabs load from here)
 2021-11-28 11:35:24 +01:00
henk717 b9c7e33410
Switch to official transformers 
Official transformers is now superior, switching over to allow Colab's to use it.
 2021-11-28 05:13:05 +01:00
henk717 939719214d
Merge pull request #40 from VE-FORBRYDERNE/patch 
Allow bad words filter to ban <|endoftext|> token
 2021-11-27 19:23:01 +01:00
Gnome Ann 9f51c42dd4 Allow bad words filter to ban <|endoftext|> token 
The official transformers bad words filter doesn't allow this by
default. Finetune's version does allow this by default, however.
 2021-11-27 11:42:06 -05:00
henk717 2bc93ba37a
Whitelist 6B in breakmodel 
Now that we properly support it, allow the menu option to use breakmodel
 2021-11-27 10:09:54 +01:00
henk717 b56ee07ffa
Fix for CPU mode 
Recent optimizations caused the CPU version to load in an incompatible format, now we convert it back to the correct format after loading it efficiently first.
 2021-11-27 05:34:29 +01:00
henk717 56c2e619f9 ColabKobold 
A brand new launcher to power the colab's, you can use https://henk.tech/ckds as a short URL which points towards this github
 2021-11-27 03:44:08 +01:00
henk717 3b976c9af7 Updated defaults 
Transformers official by default, no more Git versions
 2021-11-27 03:14:47 +01:00
henk717 6008d4f3a5
Merge pull request #39 from VE-FORBRYDERNE/breakmodel 
Official transformers 6B breakmodel support and more RAM-efficient model loading
 2021-11-27 01:11:48 +01:00
Gnome Ann e5e2fb088a Remember to actually import `GPTJModel` 2021-11-26 12:38:52 -05:00
Gnome Ann 871ed65570 Remove an unnecessary `**maybe_low_cpu_mem_usage()` 2021-11-26 11:42:04 -05:00
Gnome Ann a93a76eb01 Load model directly in fp16 if using GPU or breakmodel 2021-11-26 10:55:52 -05:00
Gnome Ann 95aff61781 Don't pin CPU layers after running out of pinned memory 2021-11-26 10:31:15 -05:00
Gnome Ann 32e1d4a7a8 Enable `low_cpu_mem_usage` 2021-11-25 18:09:25 -05:00
Gnome Ann 25c9be5d02 Breakmodel support for GPTJModel 2021-11-25 18:09:16 -05:00
Gnome Ann f8bcc3411b In breakmodel mode, move layers to GPU as soon as model loads 
Rather than during the first generation.
 2021-11-25 11:44:41 -05:00
henk717 978dc486a5
Merge pull request #38 from VE-FORBRYDERNE/warp 
Move TFS warper code into aiserver.py
 2021-11-24 23:45:28 +01:00
Gnome Ann cbb6efb656 Move TFS warper code into aiserver.py 2021-11-24 13:36:54 -05:00
henk717 96e1d98b7e
Merge branch 'KoboldAI:main' into united 2021-11-24 08:24:08 +01:00
henk717 36b9161667
Portability Bugfix 
Fix an issue where the launcher does not work if the drive is not C: on some systems.
 2021-11-24 08:23:08 +01:00
henk717 a2c82bbcc8 num_layers fixes 
As requested by VE_FORBRYDERNE (Possibly implemented it on to many places, needs testing but since the other one is already broken I am committing it first so I can more easily test)
 2021-11-24 03:44:11 +01:00
henk717 d7a2424d2d No Half on CPU 
Should fix CPU executions
 2021-11-23 17:14:01 +01:00
henk717 11c64c3fe7
Merge pull request #37 from VE-FORBRYDERNE/patch 
Use model.config.n_layer if model.config.num_layers doesn't exist
 2021-11-23 17:02:51 +01:00
Gnome Ann be0881a8d0 Use model.config.n_layer if model.config.num_layers doesn't exist 2021-11-23 10:09:24 -05:00
henk717 c0df03fc55
Merge pull request #36 from VE-FORBRYDERNE/sp 
Fix a typo in tpu_mtj_backend.py
 2021-11-23 14:23:10 +01:00
Gnome Ann 691febacd6 Fix a typo in tpu_mtj_backend.py 2021-11-22 12:53:19 -05:00
henk717 d877190258
Merge pull request #35 from VE-FORBRYDERNE/sp 
Softprompt support for the TPU backend
 2021-11-22 00:33:31 +01:00
Gnome Ann 9b8bcb5516 Always convert soft prompt to float32 if using TPU backend 
TPUs do not support float16. Attempting to use a float16 soft prompt
throws an error.
 2021-11-21 18:22:10 -05:00
Gnome Ann e068aa9f26 Add soft prompt support to TPU backend 2021-11-21 18:08:04 -05:00
henk717 a60e7d3310
Merge pull request #34 from VE-FORBRYDERNE/comments 
Add support for comments
 2021-11-21 16:24:37 +01:00
Gnome Ann df2768b745 Simplify the comment regex 2021-11-21 01:09:19 -05:00
Gnome Ann 7ab0d96b8a Change the comment regex again to use fixed-length lookbehind 2021-11-21 01:06:31 -05:00
Gnome Ann a1c378deea Fix CSS issues when editing a chunk that has a comment 2021-11-21 00:48:43 -05:00
Gnome Ann 624cfbd5a4 Use a smarter regex for comments 
If the beginning of the comment is at the beginning of a line AND the
end of a comment is at the end of a line, an additional newline will now
be ignored so that the AI doesn't see a blank line where the comment
was.

For example, consider the following message:
```
Hello
<|This is
  a comment|>
World
```

The AI will now see this:
```
Hello
World
```

instead of this:
```
Hello

World
```
 2021-11-21 00:42:57 -05:00
Gnome Ann a51f88aeb3 Also apply comment formatting to prompt in `refresh_story()` 2021-11-21 00:26:45 -05:00