kwaroran
70daaff160
Add llamacpp python scripts
2024-01-12 12:11:58 +09:00
kwaroran
b4b461288d
Add Python installation and setup functionality
2024-01-12 12:02:06 +09:00
kwaroran
11ae0266d9
Update version to 1.73.2
2024-01-11 21:50:50 +09:00
kwaroran
18f85a321f
Refactor BotSettings.svelte layout
2024-01-11 21:50:22 +09:00
kwaroran
a319eedee1
Add experimental support for Claude AWS
2024-01-11 21:50:04 +09:00
kwaroran
6031ecea32
Fix OpenAI Fixer plugin
2024-01-11 21:41:55 +09:00
kwaroran
1f2ee464d1
Remove unused function isAPNG from parser.ts
2024-01-10 07:09:27 +09:00
kwaroran
264211fdfd
Refactor image.ts to use checkImageType instead of isAPNG
2024-01-10 07:08:13 +09:00
kwaroran
fd0de264e9
Update version to 1.73.1
2024-01-10 06:56:00 +09:00
kwaroran
f66d8f66a8
Change FontColorItalic color in highcontrast mode
2024-01-10 06:54:40 +09:00
kwaroran
6b88602673
Fix conditional statement in ProomptItem.svelte
2024-01-10 06:53:38 +09:00
kwaroran
a2f81fefd8
Fix google api key display
2024-01-09 20:03:55 +09:00
kwaroran
3610c2c9c0
Update version to 1.73.0
2024-01-09 00:31:20 +09:00
kwaroran
350bc66851
Add support for WebLLM
2024-01-09 00:27:58 +09:00
kwaroran
1ee7107153
Fix conversion units in metricaPlugin
2024-01-08 16:01:21 +09:00
kwaroran
7db7b71202
Move openrouter settings to BotSettings.svelte
2024-01-08 09:25:37 +09:00
kwaroran
5d7bc64ed1
Fix price calculation in openRouterModels function
2024-01-08 09:23:26 +09:00
kwaroran
414fad13ed
Update price calculation in openRouterModels function
2024-01-08 09:14:28 +09:00
kwaroran
f8aba003fb
Update version to 1.72.0
2024-01-08 09:13:19 +09:00
kwaroran
a490dbde47
Add new language keys and checkboxes for openrouter fallback and middle out
2024-01-08 09:10:52 +09:00
kwaroran
62a6577368
Add openrouterFallback and openrouterMiddleOut options
2024-01-08 09:09:12 +09:00
kwaroran
aaa5843c51
Add custom chain of thought feature and max thought tag depth setting
2024-01-08 09:03:12 +09:00
kwaroran
ecbbc8e85c
Update fileURL in runVITS to Use localModelPath
2024-01-06 23:21:38 +09:00
kwaroran
229d974d75
Rename tfCache
2024-01-06 23:17:33 +09:00
kwaroran
4be7a6762c
Update local model path to use remote URL
2024-01-06 23:16:13 +09:00
kwaroran
3a8b09586f
fix URL matching logic in initTransformers function
2024-01-06 23:12:49 +09:00
kwaroran
8617257298
Update version 1.71.4
2024-01-06 23:08:15 +09:00
kwaroran
f638866308
Fix error handling
2024-01-06 22:43:59 +09:00
kwaroran
8eccda086d
Refactor URL handling in initTransformers function
2024-01-06 22:41:08 +09:00
kwaroran
de17fe3afa
Update version to 1.71.3 and add file URL mapping
2024-01-06 22:31:42 +09:00
kwaroran
e974b5ee7f
Match URLs to cache server
2024-01-06 22:21:45 +09:00
kwaroran
c3d7210cc3
Refactor caching logic in sw.js and transformers.ts
2024-01-06 21:18:36 +09:00
kwaroran
afd085bd93
Fix tfCache initialization and assignment
2024-01-06 20:50:49 +09:00
kwaroran
46ee706399
Add initialization function for Transformers and update model paths
2024-01-06 20:49:34 +09:00
kwaroran
85cd1cbc65
Add 404 response for 'tf' resource in sw.js
2024-01-06 20:32:19 +09:00
kwaroran
da77f12f7e
Update version to 1.71.2
2024-01-06 20:25:31 +09:00
kwaroran
a9872b3d5d
Update localModelPath in transformers.ts
2024-01-06 20:25:03 +09:00
kwaroran
1114d5b61b
Update version to 1.71.1
2024-01-06 19:46:19 +09:00
kwaroran
229aeced06
Merge branch 'main' of https://github.com/kwaroran/RisuAI
2024-01-06 19:45:57 +09:00
kwaroran
5a305a8f10
Fix sw register temp
2024-01-06 19:45:50 +09:00
kwaroran
cba3ff802c
Add selectable tokenizer supports on Ooba ( #281 )
...
# PR Checklist
- [ ] Did you check if it works normally in all models? *ignore this
when it dosen't uses models*
- [ ] Did you check if it works normally in all of web, local and node
hosted versions? if it dosen't, did you blocked it in those versions?
- [ ] Did you added a type def?
# Description
I write simple changes on code, which allow user to choose tokenizers.
As I write on https://github.com/kwaroran/RisuAI/issues/280 , differences
in tokenizers makes error when use mistral based models.
As I'm not good at javascript, I simply implement this work by write
name of tokenizer model, and select one on tokenizer.ts file.
I test it on my node RisuAI and I send long context to my own server.
As result, ooba returned 15858 as prompt tokens.
And as I test on official tokenizer implementations, it shows 1k
differences between llama tokenizer and mistral tokenizer.
So I think adding this option will help users use oobabooga with less
error.
2024-01-06 19:16:58 +09:00
kwaroran
8ba0d10d56
Update version to 1.71.0
2024-01-06 19:13:57 +09:00
kwaroran
70f25968b5
add transformers remoteHost again
2024-01-06 19:12:18 +09:00
kwaroran
497e0c6dfb
Update service worker and remote host URLs
2024-01-06 19:10:21 +09:00
kwaroran
f4d6fcb38c
Update characterCards.ts with VITS export support
2024-01-06 07:05:20 +09:00
kwaroran
7344e566f4
Add model selection for VitsModel
2024-01-06 06:45:18 +09:00
kwaroran
66c6511684
Refactor sw.js to support custom headers in registerCache function
2024-01-06 01:28:00 +09:00
kwaroran
0ca4ec3695
Add VITS support
2024-01-06 00:28:06 +09:00
kwaroran
cfdd60bead
Remove TransformersBodyType
2024-01-05 23:58:23 +09:00
justpain02
ff4c67b993
Add selectable tokenizer supports on Ooba
2024-01-05 23:57:59 +09:00
