kwaroran
bfb6633f89
Add risu rcc for export
2024-02-02 18:07:03 +09:00
bangonicdd
43efaa2313
Change to inline style from reactive declarations
2024-02-01 00:16:06 +09:00
kwaroran
afea17dfb3
Update model options in ModelList.svelte and request.ts
2024-01-26 04:24:02 +09:00
gdosu
9699c77415
increase max value
2024-01-25 01:41:06 +09:00
gdosu
87fbf07bcf
Reduced duplicated call
2024-01-24 20:38:18 +09:00
gdosu
f524cf0f95
remove test log
2024-01-24 13:54:33 +09:00
gdosu
a550c870f3
Add memory limit border thickness
2024-01-24 13:34:19 +09:00
kwaroran
608f29ba13
Fix frequency and presence penalty calculations
2024-01-17 11:26:58 +09:00
kwaroran
4d27bc49c0
Add commands
2024-01-17 07:58:36 +09:00
kwaroran
1e062d3077
Rename removePunctuationHypa and change functionality
2024-01-17 07:07:38 +09:00
kwaroran
ce5e764311
Update frequency and presence penalty slider max value to 2
2024-01-16 17:58:12 +09:00
kwaroran
1b1c6ad2fd
Refactor code for local models
2024-01-16 17:52:33 +09:00
kwaroran
9db4810bbc
Experimental llamacpp support
2024-01-16 10:56:23 +09:00
kwaroran
52940af010
Add option to remove punctuation for HypaMemory
2024-01-15 18:00:19 +09:00
kwaroran
5239423582
Rename updateLog.ts
2024-01-15 13:01:28 +09:00
kwaroran
31724901d2
Fix Added patch note notification
2024-01-15 13:01:04 +09:00
kwaroran
5379e2430f
Remove unused setting
2024-01-13 10:54:56 +09:00
kwaroran
9b39de366d
Add advanced settings descriptions
2024-01-13 10:54:37 +09:00
kwaroran
921a9cae1e
Remove experimental tag from genTimes
2024-01-13 10:42:41 +09:00
kwaroran
18980f0639
Refactor OtherBotSettings.svelte: Remove experimental tag
2024-01-13 10:41:49 +09:00
kwaroran
b4b461288d
Add Python installation and setup functionality
2024-01-12 12:02:06 +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
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
350bc66851
Add support for WebLLM
2024-01-09 00:27:58 +09:00
kwaroran
7db7b71202
Move openrouter settings to BotSettings.svelte
2024-01-08 09:25:37 +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
aaa5843c51
Add custom chain of thought feature and max thought tag depth setting
2024-01-08 09:03:12 +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
7344e566f4
Add model selection for VitsModel
2024-01-06 06:45:18 +09:00
kwaroran
0ca4ec3695
Add VITS support
2024-01-06 00:28:06 +09:00
justpain02
ff4c67b993
Add selectable tokenizer supports on Ooba
2024-01-05 23:57:59 +09:00
kwaroran
e5c65d7b09
[fix] welcome freezing
2024-01-04 17:09:07 +09:00
kwaroran
5093fd9d0b
[fix] high constrast by default
2024-01-04 03:54:13 +09:00
kwaroran
4f77504d3f
[feat] add translate replace regex
2024-01-04 03:37:05 +09:00
kwaroran
a13fdced2e
[fix] openai max context
2024-01-04 02:36:45 +09:00
kwaroran
036b23dbdc
[fix] block native
2024-01-04 02:35:08 +09:00
kwaroran
499e91ce6f
[fix] mobile saving
2024-01-04 02:34:22 +09:00
kwaroran
32e3060b19
[feat] better openrouter support
2024-01-04 02:32:53 +09:00
kwaroran
1d5d69b71b
[feat] finish new welcome
2024-01-04 02:14:05 +09:00
kwaroran
d36399e409
[feat] new template
2024-01-03 20:17:03 +09:00
kwaroran
23ef56cb33
[feat] fix horde support
2024-01-03 19:36:47 +09:00
kwaroran
99743f581a
[feat] add top_k for openrouter
2024-01-03 19:03:24 +09:00
kwaroran
f3cf1957f1
[feat] new welcome screen
2024-01-03 02:31:19 +09:00
kwaroran
0fb9beb5ea
[fix] newyear
2024-01-01 00:02:19 +09:00
kwaroran
151c7450d3
[fix] to localstring on chat
2023-12-31 22:28:38 +09:00
kwaroran
fa7da4c9e6
[fix] static
2023-12-31 22:25:03 +09:00
kwaroran
6d5e48b024
[fix] remove special day
2023-12-31 22:20:54 +09:00
