50defbaa04
Merge pull request #32 from VE-FORBRYDERNE/loader
...
Move the TPU backend code into this repository
2021-11-20 01:01:18 +01:00
286ed51534
Add a requirements.txt for TPU backend
2021-11-19 18:20:02 -05:00
a65c4de840
Integrate TPU backend
...
This commit puts the TPU backend code directly in to the KoboldAI code
to make it easier to modify.
2021-11-19 18:06:57 -05:00
b926170fb0
Merge branch 'KoboldAI:main' into united
2021-11-19 00:05:21 +01:00
4e791b2f2d
Merge pull request #82 from VE-FORBRYDERNE/editor
...
Fix some editor issues in Firefox and possibly mobile browsers
2021-11-19 00:04:31 +01:00
bb51198f40
Fix some editor issues in Firefox and possibly mobile browsers
...
When Firefox 93.0 was released, they broke the ability to edit text
across multiple chunks or across multiple paragraphs. If you tried,
nothing would happen.
Also, we are no longer using Mutation Observers to detect when a chunk
is modified. We are now using the beforeinput event.
2021-11-18 13:18:18 -05:00
4a678deaa5
Merge branch 'KoboldAI:main' into united
2021-11-18 06:51:44 +01:00
9b73d6a913
Merge pull request #81 from VE-FORBRYDERNE/patch
...
Replace slashes in model name with underscores
2021-11-18 06:51:21 +01:00
b25c54cf91
Polishing and Optimizations
...
Multiple things have changed, for now models default to half mode even on the official transformers to make sure its as efficient on the GPU as finetune's. GPU selection is streamlined and cache files are now stored inside the KoboldAI folder (for the most part). A new command line parameter to force the models to run at their full size still needs to be added for the few users that would want a quality bump at the cost of ram.
2021-11-18 00:06:57 +01:00
27ee45b9cc
Merge pull request #31 from VE-FORBRYDERNE/cpu
...
Fix gen_in device logic in generate()
2021-11-17 22:42:31 +01:00
2f0b673b28
Fix gen_in device logic in generate()
2021-11-17 16:37:37 -05:00
e71271933a
Merge pull request #29 from VE-FORBRYDERNE/hidden-size
...
Fix hidden size detection for GPTJForCausalLM
2021-11-17 22:30:24 +01:00
26eb2cb6ce
Merge pull request #30 from VE-FORBRYDERNE/dynamic-scan
...
Support for multiple gens per action with dynamic scan
2021-11-17 22:30:12 +01:00
a1bc10246c
Support for multiple gens per action with dynamic scan
2021-11-17 16:17:59 -05:00
485034b6bb
ROCm Conda
...
Allows anyone to easily create a ROCm compatible conda environment. Currently set to the newer transformers, you can edit the github link if you want the finetune one.
2021-11-17 22:15:01 +01:00
98a72e34a4
Replace slashes in model name with underscores
2021-11-17 15:36:36 -05:00
ab1a65f13a
Fix hidden size detection for GPTJForCausalLM
2021-11-15 11:56:02 -05:00
ffdc5fc276
Merge pull request #28 from VE-FORBRYDERNE/gpu
...
Use the old GPU generation mode when all layers are on one GPU
2021-11-15 07:33:48 +01:00
17d07b280a
Correct `gpu_layers` to `gpu_blocks`
2021-11-14 21:08:49 -05:00
805cb0c8b9
Make sure device_config() still works with all layers on CPU
2021-11-14 18:46:00 -05:00
80aee07816
Use old GPU-only generation if all layers are on the same GPU
...
Apparently, this mode uses less RAM than breakmodel does.
2021-11-14 18:42:18 -05:00
b0ab30cec4
Re-enable GPU-only generation option
2021-11-14 18:24:51 -05:00
3e38b462c6
Hidden Size fix for GPT2 Custom
...
Replaced the JS Hidden Size load with the newer function to fix these models
2021-11-14 16:40:04 +01:00
f227a876c0
Merge pull request #27 from VE-FORBRYDERNE/united
...
Merge branch 'main' into united
2021-11-14 03:59:26 +01:00
21b19b81dd
Merge branch 'main' into united
2021-11-13 21:58:27 -05:00
7b47a8457a
Merge pull request #80 from VE-FORBRYDERNE/main
...
Improved Unix Support
2021-11-14 03:56:56 +01:00
ecea169553
Improved Unix Support
...
Changes the line-endings to the Unix format and sets KoboldAI to launch with Python3 if executed directly.
(cherry picked from commit 5b0977ceb6807c0f80ce6717891ef5e23c8eeb77)
2021-11-13 21:54:32 -05:00
1596a238f7
Breakmodel automation
...
The only changes are a small addition to the breakmodel section where GPU0 is automatically chosen if the CLI options are used without specifying breakmodel. Lineendings have been changed to Linux formatting for compatibility reasons.
2021-11-14 03:13:52 +01:00
8a916116e3
Remove device=0 because of incompatibility
...
Device=0 breaks some of the pytorch implementations, removed to restore hardware compatibility to 0.16 levels.
2021-11-14 02:33:27 +01:00
4bcffc614e
Allow directly running KoboldAI from CLI in Linux
...
Its made for Python3, so we assume python3 is installed in its usual location. If it isn't you can always run it yourself with whatever command you used prior to this change.
2021-11-14 01:57:43 +01:00
21ae45e9ab
Merge branch 'KoboldAI:main' into united
2021-11-11 17:05:39 +01:00
8ad3863854
Merge pull request #26 from VE-FORBRYDERNE/sp-patch
...
More softprompting bug fixes
2021-11-11 17:05:32 +01:00
4ebece0a6f
Merge pull request #79 from VE-FORBRYDERNE/broadcast-patch
...
Don't broadcast emit calls inside do_connect()
2021-11-11 17:05:13 +01:00
1fadcbe1e3
Send allowsp command on connect instead of on startup
2021-11-11 00:18:46 -05:00
2fe815e092
Don't broadcast emit calls inside do_connect()
...
This prevents the "thinking" animation from appearing on top of the
submit button under certain circumstances:
* When someone connects to the KoboldAI server while the model is
generating (occurs after generation finishes)
* Occasionally, the browser may suddenly disconnect and reconnect from
Flask-SocketIO during generation, which causes the same problem
2021-11-11 00:14:12 -05:00
11b0291bc4
Use model.transformer.embed_dim if model.transformer.hidden_size doesn't exist
2021-11-10 17:47:14 -05:00
752e19a2bb
Fix vars.modeldim not always being set
2021-11-10 17:38:30 -05:00
e6599db78f
Merge pull request #25 from VE-FORBRYDERNE/united
...
Merge branch 'main' into united
2021-11-10 03:37:43 +01:00
2679df9664
Merge branch 'main' into united
2021-11-09 21:33:14 -05:00
c2371cf801
Merge pull request #23 from VE-FORBRYDERNE/scan-test
...
Dynamic world info scan
2021-11-10 03:31:42 +01:00
d5a26e8c20
Fixed root permissions
...
The Docker has been changed to no longer run these commands as root, added root permissions for the relevant commands to fix the docker.
2021-11-10 03:17:12 +01:00
4af0d9dabd
Merge pull request #78 from VE-FORBRYDERNE/patch
...
Allow remote mode to load from client-side story files
2021-11-06 16:58:05 +01:00
02a56945de
Version bump
2021-11-06 11:50:56 -04:00
bc0f9c8032
Allow remote mode to load from client-side story files
...
(cherry picked from commit a1345263df
2021-11-06 11:48:20 -04:00
7ea6f58b1a
Resolve merge conflict
2021-11-05 11:03:50 -04:00
a1345263df
Merge pull request #22 from VE-FORBRYDERNE/filereader
...
Allow remote mode to load from client-side story files
2021-11-05 02:30:20 +01:00
7a0b0b0d2d
Remove debug logging from application.js
2021-11-04 19:36:45 -04:00
7c099fe93c
Allow remote mode to load from client-side story files
2021-11-04 19:33:17 -04:00
2829c45ed6
Merge pull request #21 from VE-FORBRYDERNE/united
...
Softprompting bug fixes
2021-11-04 15:38:21 +01:00
81bd058caf
Make sure calcsubmitbudget uses the correct reference to vars.actions
2021-11-03 18:57:02 -04:00
henk717
Gnome Ann