rixty
/
SillyTavern
mirror of https://github.com/SillyTavern/SillyTavern.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
4,624 Commits 11 Branches 89 Tags 316 MiB
Commit Graph

4624 Commits

Author SHA1 Message Date
Cohee facc5d078a
Merge pull request #2084 from StefanDanielSchwarz/staging 
Command R context+instruct presets
 2024-04-14 01:19:31 +03:00
Cohee f074fb0eee Update content index 2024-04-14 01:18:54 +03:00
Stefan Daniel Schwarz 1284783c82 Command R system prompt simplified 2024-04-13 21:44:52 +02:00
Cohee ef917ebe4e Add JSDoc comments 2024-04-13 21:51:36 +03:00
Cohee f0bce909f6
Merge pull request #2076 from steve02081504/staging 
fix #2071: Set window title as `SillyTavern WebServer`
 2024-04-13 21:47:44 +03:00
Cohee 306bff0a92 #2085 Switch to async token counters 2024-04-13 21:33:19 +03:00
Cohee 1c4bad35b2 #2085 Implement async token counting 2024-04-13 21:05:31 +03:00
steve02081504 86906576b3 Merge remote-tracking branch 'upstream/staging' into staging 2024-04-14 01:39:49 +08:00
steve02081504 f48d90a9c9 some fixes 2024-04-14 01:39:28 +08:00
Cohee ba397dd2a8 #2062 Extend unlock for MakerSuite models 2024-04-13 20:09:51 +03:00
Cohee ba312d316c Merge branch 'release' into staging 2024-04-13 20:04:52 +03:00
Cohee 8ae9212cc5 #2075 Fix Draw Things auth 2024-04-13 20:02:54 +03:00
Cohee 3a4405016c #2075 Fix Draw Things auth 2024-04-13 20:01:17 +03:00
Stefan Daniel Schwarz fdac9314ad Command R context+instruct presets 2024-04-13 15:49:09 +02:00
Touch-Night d7d3787088 Some more fixes 2024-04-13 21:30:48 +08:00
Touch-Night 985b77d407 Improve Chinese translation 2024-04-13 20:40:02 +08:00
Yokayo 4fb6cbc3fb
Update readme-ru_ru.md 2024-04-13 19:31:07 +07:00
Cohee de8339f77b Fix ESLint 2024-04-13 15:24:49 +03:00
Yokayo ae78112311
Add link to readme-ru_ru 2024-04-13 19:23:51 +07:00
Cohee f79f335491
Merge pull request #2078 from LenAnderson/fix-popup 
Fix popup
 2024-04-13 15:23:39 +03:00
Yokayo e62bdab2c6
Add link to readme-ru_ru 2024-04-13 19:23:10 +07:00
Cohee 6c8b29a39a
Merge pull request #2079 from Zhongyi-Lu/dev-forward-ip 
Check forwarded IP in WhiteList
 2024-04-13 15:22:53 +03:00
Yokayo 4ba3f5b351
Markup 2024-04-13 19:18:34 +07:00
Yokayo 1c515c3a5e
Fix markup 2024-04-13 19:02:28 +07:00
Yokayo cb472fc912
Add link to readme-ru_ru 2024-04-13 18:51:03 +07:00
Yokayo 333df46680
Add readme-ru_ru 2024-04-13 18:50:15 +07:00
kingbri 913085ba74 Expressions: Let the user know if classification failed 
Send a message if the classifer fails and fallback to the default
expression.

Signed-off-by: kingbri <bdashore3@proton.me>
 2024-04-13 01:29:54 -04:00
Zhongyi Lu 792be63c5c fix: whitelist in real-ip 2024-04-12 22:03:36 -07:00
steve02081504 64e8bc1911 Merge remote-tracking branch 'upstream/staging' into staging 2024-04-13 10:51:16 +08:00
LenAnderson 278ec029f5 add missing cancelButton setting to callGenericPopup 2024-04-12 20:50:14 -04:00
LenAnderson 91558ad9ea add enter to submit on input type 2024-04-12 20:49:55 -04:00
Cohee 89d3673010 Fix npm audit 2024-04-12 22:13:29 +03:00
Cohee 2af4747936 Bump package version 2024-04-12 22:09:09 +03:00
steve02081504 072e09d0ed fix #2071 2024-04-13 00:51:34 +08:00
kingbri 8c4dd6ce1e Expressions: Ignore stopping strings 
Don't use stopping strings when triggering a classify generation.

Signed-off-by: kingbri <bdashore3@proton.me>
 2024-04-12 09:57:09 -04:00
Cohee 9c218455c4 [chore] Run ESLint 2024-04-12 14:22:12 +03:00
Cohee b09cabaeb2
Merge pull request #2073 from ThisIsPIRI/hide 
Performance improvement for /hide, /unhide
 2024-04-12 14:19:59 +03:00
Cohee d9baff45bb Fix return types. Async functions must return a Promise. 2024-04-12 14:18:59 +03:00
ThisIsPIRI 6603e33fd8 Add hideChatMessage back 2024-04-12 20:05:58 +09:00
ThisIsPIRI 208e089761 Replace hideChatMessage with hideChatMessageRange 2024-04-12 16:03:50 +09:00
kingbri bea63a2efe Expressions: Remove TalkingHead from choices 
This is a sub-choice under extras.

Signed-off-by: kingbri <bdashore3@proton.me>
 2024-04-12 01:59:44 -04:00
kingbri 6b656bf380 Expressions: Classify using LLM 
Rather than using a separate BERT model to classify the last message,
use the LLM itself to get the classified expression label as a JSON
and set that as the current sprite. Doing this should take more information
into consideration and cut down on extra processing.

This is made possible by the use of constrained generation with JSON
schemas. Only available to TabbyAPI since it's the only backend that
supports the use of JSON schemas, but there can hopefully be a way
to use this with other backends as well.

Intercepts the generation and sets top_k = 1 (for greedy sampling)
and the json_schema to an emotion enum. Doing this also prevents
reingestion of the entire context every time a message is sent and
then asked to be classified, which doesn't compromise the chat
experience.

Signed-off-by: kingbri <bdashore3@proton.me>
 2024-04-12 01:55:16 -04:00
RossAscends 626c93a1ab Merge branch 'staging' of https://github.com/Cohee1207/SillyTavern into staging 2024-04-12 08:21:18 +09:00
RossAscends 94f14340ae add background image name reporting for /bg with no args 2024-04-12 08:21:17 +09:00
sasha0552 7348199f73
Add llama.cpp slots info endpoint (#2070) 2024-04-11 23:53:32 +03:00
Cohee 356f1f9c39 Clean-up non-character state checks 2024-04-11 23:50:01 +03:00
Cohee 123131074c Change built-in extensions template render to async 2024-04-11 23:38:44 +03:00
Cohee 16cabb38ad Fix init order in RA mods 2024-04-11 22:47:28 +03:00
Cohee 3da9fb4efe Switch to module exports 2024-04-11 22:39:42 +03:00
Cohee 369c3512c0 Add async template renderer 2024-04-11 22:36:23 +03:00