rixty
/
KoboldAI-Client
mirror of https://github.com/KoboldAI/KoboldAI-Client.git
1
1
Fork 0
Code Issues Projects Releases Wiki Activity
1,053 Commits 1 Branch 5 Tags 120 MiB
Commit Graph

1053 Commits

Author SHA1 Message Date
Henky!! 965b5b5b04 Install Improvements 2022-04-05 01:52:46 +02:00
henk717 ee682702ee
Merge branch 'KoboldAI:main' into united 2022-04-05 01:35:22 +02:00
Henky!! 8153f21d5c Convo 6B 2022-04-05 01:33:51 +02:00
henk717 04707abde6
Merge pull request #109 from VE-FORBRYDERNE/requirements 
Remove Ray from requirements_mtj.txt
 2022-04-04 19:17:56 +02:00
Gnome Ann 66bc7e10bf Remove Ray from requirements_mtj.txt 
I made some changes recently to mesh transformer JAX so that we don't
need Ray anymore. This should make the installation a little faster.
 2022-04-04 12:42:33 -04:00
henk717 0882ba165c
Merge pull request #108 from VE-FORBRYDERNE/lazy-loader 
Lazy loader Python 3.6 compatibility
 2022-04-03 01:15:48 +02:00
Gnome Ann fabbdf2bb1 Lazy loader Python 3.6 compatibility 
The current lazy loader relies on a feature of the Python zipfile module
that was added in Python 3.7.0:

https://bugs.python.org/issue22908

This commit adds compatibility for Python 3.6.
 2022-04-02 15:02:54 -04:00
Noli d9670f4e16 Revert "add colab cell to start ECILA" 
This reverts commit 231418e15e.
 2022-03-29 07:23:36 +02:00
Noli 231418e15e add colab cell to start ECILA 2022-03-29 07:21:23 +02:00
henk717 8368b20421
Merge pull request #107 from VE-FORBRYDERNE/typical 
Typical sampling needs to use nansum instead of sum
 2022-03-28 11:13:38 +02:00
Gnome Ann 67e28d2b5c Typical sampling needs to use nansum instead of sum 
If `probs` is zero then `log_probs` will be negative infinity, and the
calculation of `neg_entropy` would then give NaN because zero times
infinity is a mathematically indeterminate value.

We need to use nansum so that those NaN values are treated as zeros to
ignore them in the entropy calculation.
 2022-03-28 00:02:31 -04:00
Henky!! e644963564 OpenAI Fixes 2022-03-28 02:02:37 +02:00
henk717 77ae893f4d
Merge pull request #106 from VE-FORBRYDERNE/typical 
Typical sampling
 2022-03-28 00:14:09 +02:00
Gnome Ann e2cd49d552 Typo fix in `TypicalLogitsWarper` 2022-03-27 17:08:57 -04:00
Gnome Ann bbd0a83fef Fix `TypicalLogitsWarper` argument typing 2022-03-27 16:59:23 -04:00
Gnome Ann d5989d4c62 Hide division by zero warning in JAX typical filter 
This warning happens when `np.log` gets an input containing zeros.
In that case, NumPy will throw a warning and output negative infinity.

Negative infinity is the correct behaviour here, so we can safely ignore
the warning.
 2022-03-27 16:57:12 -04:00
Gnome Ann 20e48b11d7 Typical sampling 2022-03-27 16:25:50 -04:00
Noli aa8de64aa4 fix default port 2022-03-25 23:26:27 +01:00
Noli 3e003d3b42 add port to the command options 2022-03-25 22:18:28 +01:00
Noli 076c6c8efa update slider value without waiting for socketio 2022-03-25 22:18:00 +01:00
Noli 72b74d9ab6 fix tabs 2022-03-25 20:46:08 +01:00
Noli 6aaa8d026f semicolon 2022-03-25 20:44:41 +01:00
Noli 8270d92073 fix wrong this scope 2022-03-25 20:44:25 +01:00
Noli 6ed50ee1e9 make the throttle timer a dict to keep track of which slider has been changed 2022-03-25 20:37:45 +01:00
nolialsea 1de4944d46
Add throttle closure for settings sliders 
Adds a throttling closure to add a waiting time before calling a callback,
Uses this closure to throttle the event fired by socketio on slider value change
 2022-03-25 20:08:56 +01:00
henk717 e4c72ca2e5
Merge pull request #104 from VE-FORBRYDERNE/retry-randomgame 
Allow regenerating random story using Retry button
 2022-03-24 12:57:04 +01:00
Gnome Ann 0348970b19 Make sure AI is not busy when using retry to regenerate random story 2022-03-23 22:09:35 -04:00
Gnome Ann 4832dd6f37 Allow regenerating random story using Retry button 
Commit b55e5a8e0b removed this feature, so
this commit adds it back.
 2022-03-23 13:39:46 -04:00
henk717 38d78d10db
Merge pull request #103 from VE-FORBRYDERNE/neox 
Divide GPT-NeoX replicated bias layers by 4 again instead of by 8
 2022-03-21 02:19:32 +01:00
henk717 cf99f02ca5 Merge branch 'main' into united 2022-03-20 19:22:53 +01:00
henk717 20eab085dd Fix AutoSave Toggle 2022-03-20 19:12:11 +01:00
henk717 5c795609e4 KML Fix 2022-03-20 13:10:56 +01:00
Gnome Ann 73aecc0510 Divide NeoX replicated bias layers by 4 again instead of by 8 2022-03-20 01:04:55 -04:00
henk717 f1487a4551 New Linux Runtime 2022-03-20 00:00:21 +01:00
henk717 a7f652f293
Merge pull request #101 from VE-FORBRYDERNE/neox 
GPT-NeoX-20B support in Colab TPU instances
 2022-03-19 09:56:15 +01:00
Gnome Ann 05fc46b253 Changing this again to divide by 8 2022-03-19 02:09:41 -04:00
Gnome Ann b1125a6705 Add EOS and padding token to default NeoX badwords 2022-03-19 01:30:02 -04:00
Gnome Ann 6c20d0d657 Nevermind, dividing by 4 is actually correct... 2022-03-19 00:55:04 -04:00
Gnome Ann f16b61ec77 Should divide NeoX replicated parameters by 8 (not by 4) 
Also, suppresses the PyTorch 1.11 warning about transposing tensors with
ndim != 2 in the new code
 2022-03-19 00:48:33 -04:00
Gnome Ann c2c139e940 Change default PE type for NeoX to `neox_rotary` 2022-03-19 00:26:04 -04:00
Gnome Ann 85a4959efa Merge branch 'united' into neox 2022-03-18 11:19:03 -04:00
henk717 f581fe89cb Torch version changes 2022-03-17 21:11:36 +01:00
henk717 9e9c1c3fe0
Merge pull request #100 from VE-FORBRYDERNE/patch 
Add PyTorch 1.11 support for lazy loader
 2022-03-17 21:06:38 +01:00
Gnome Ann c444260eac Silence PyTorch warning about transposing tensors with dimension != 2 2022-03-17 15:16:56 -04:00
Gnome Ann ef21ab9c91 PyTorch 1.9 lazy loader compatibility bugfix 2022-03-17 14:10:51 -04:00
Gnome Ann eaf190469d Add PyTorch 1.11 support for lazy loader 2022-03-17 12:51:41 -04:00
henk717 9235754eb9 Dependency Fixes 2022-03-17 00:35:59 +01:00
henk717 a3e5e052b3 Newer umamba + slope tweak 2022-03-16 18:34:02 +01:00
Gnome Ann 95c4251db9 Print two newlines before loading HF models 2022-03-15 13:58:53 -04:00
Gnome Ann 9e2848e48f Show parameter count when loading GPT-NeoX in Colab TPU instance 2022-03-15 13:55:27 -04:00