rixty
/
SillyTavern
mirror of https://github.com/SillyTavern/SillyTavern.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
5,879 Commits 11 Branches 91 Tags 295 MiB
Commit Graph

166 Commits

Author SHA1 Message Date
Cohee b62cbdeebd Merge branch 'staging' into DarokCx/release 2024-06-28 19:09:12 +03:00
Cohee bbb1a6e578 Add huggingface inference as text completion source 2024-06-28 18:17:27 +03:00
DarokCx 29ff0876a7 Added additional headers 2024-06-28 08:20:15 -04:00
DarokCx bd5592de7b Added featherless, connect button not working 2024-06-27 09:06:11 -04:00
Cohee 41ab90bb8e Support more parameters for Infermatic 2024-06-24 19:16:20 +03:00
Cohee a3dbcf3c2a Fix context and response size not being passed to Ollama 2024-06-24 03:48:34 +03:00
Cohee 1dd21caa66 Adjust number of VLLM logprobs 2024-06-09 00:59:40 +03:00
Cohee ff680f46cc Add rep_pen_slope control for koboldcpp 2024-06-05 22:05:41 +03:00
kingbri 4528655bb7 Textgen: Add multiswipe support for TabbyAPI 
Tabby now supports batching and the "n" parameter for both non-streaming
and streaming. Add this into SillyTavern.

Signed-off-by: kingbri <bdashore3@proton.me>
 2024-05-28 00:55:57 -04:00
Cohee e8b96fec02 Merge branch 'staging' into new-samplers 2024-05-22 23:26:47 +03:00
kokansei 75a1ef4304
Add DRY Samplers to ST Staging (#2211) 
* Add files via upload

* Add files via upload

* Delete public/index.html

* Add files via upload

* Delete public/scripts/textgen-settings.js

* Add files via upload

* Delete public/scripts/power-user.js

* Add files via upload

* Delete public/scripts/power-user.js

* Add files via upload

* Update power-user.js

* Update index.html

* Fix control attribution

* Fix app loading

* Put sequence breakers under DRY block

* DRY for DRY

* Update public/index.html

Co-authored-by: Philipp Emanuel Weidmann <pew@worldwidemann.com>

* Merge fix

* Add llamacpp control. Add default value for sequence breakers

* Forgot reset

---------

Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>
Co-authored-by: Philipp Emanuel Weidmann <pew@worldwidemann.com>
 2024-05-22 20:46:52 +03:00
kingbri 74b6ed97c2 Textgen: Add repetition decay for TabbyAPI 
Repetition decay softens the drop off for repetition penalty. It's
best paired with rep pen range.

Signed-off-by: kingbri <bdashore3@proton.me>
 2024-05-22 00:09:10 -04:00
kingbri 99d143263d Textgen: Add skew sampling 
Adds the option from skew sampling from exllamaV2

Signed-off-by: kingbri <bdashore3@proton.me>
 2024-05-21 23:48:33 -04:00
kingbri a12df762a0 Textgen: Add speculative_ngram for TabbyAPI 
Speculative ngram allows for a different method of speculative
decoding. Using a draft model is still preferred.

Signed-off-by: kingbri <bdashore3@proton.me>
 2024-05-21 23:37:36 -04:00
Cohee ee913be46b
Merge pull request #2266 from sasha0552/vllm-fixes 
vLLM fixes
 2024-05-19 14:23:07 +03:00
RossAscends c7232ae23c WIP textgen API custom sampler display 2024-05-19 15:06:29 +09:00
sasha0552 db5e2d95c2
vLLM fixes 
* Enable seed field for vLLM

* Enable beam search for vLLM

* Set the default length penalty to 1
(There is validation error from vLLM when beam search is disabled and the value is not equal to 1)
 2024-05-19 04:34:11 +00:00
Cohee 4227968dfa Allow using JSON schema with llamacpp server 2024-05-18 18:50:48 +03:00
Cohee c7d75b7789 llamacpp broke 2024-05-12 21:41:07 +03:00
Cohee 27ccc6b090 Minor stylistic changes 2024-05-11 11:38:22 +03:00
kingbri 62faddac8d Textgen: Add banned_strings 
TabbyAPI supports the ability to ban the presence of strings during
a generation. Add this support in SillyTavern by handling lines
enclosed in quotes as a special case.

Signed-off-by: kingbri <bdashore3@proton.me>
 2024-05-11 00:58:29 -04:00
Cohee c73bfbd7b0 Safari bruh moment 2024-05-06 21:21:03 +03:00
Cohee 7063fce2af Selectable openrouter providers 2024-05-06 19:26:20 +03:00
Cohee 05db2552b3 Fix Top K disabled state for Infermatic. 
Also an icon.
 2024-05-04 02:37:05 +03:00
Cohee 7bfd666321 Add llama 3 tokenizer 2024-05-03 23:59:39 +03:00
Cohee 7b87f44518 Clean-up API-specific settings 2024-05-03 20:02:13 +03:00
sasha0552 2bd239fe81
Initial vLLM support 2024-05-02 22:40:40 +00:00
Cohee 022c180b62 Lint and clean-up 2024-04-15 00:39:15 +03:00
Cohee 3e60919289 Specify LLM prompt in case JSON schema is not supported 2024-04-14 17:13:54 +03:00
kingbri b8b49f0012 TextgenSettings: Fix JSON schema fallback 
Did not fall back if the provided string was empty, resulting in
errors

Signed-off-by: kingbri <bdashore3@proton.me>
 2024-04-09 22:15:00 -04:00
Cohee 51b3b8bfaa Add smooth streaming 2024-04-02 14:56:15 +03:00
Cohee 04edf32ef0 Do not send dynatemp to backends if disabled 2024-04-02 11:29:49 +03:00
Cohee 0b76e1d350 Fix schema not loading from presets. Fix ESLint warnings 2024-04-02 11:23:29 +03:00
kingbri 5210db5679 Format 
Signed-off-by: kingbri <bdashore3@proton.me>
 2024-04-02 01:01:59 -04:00
kingbri 4f0322351e Sampling: Add ability to send JSON schemas 
TabbyAPI supports the ability to send JSON schemas with prompts in
addition to EBNF strings supported by outlines. Add an extra box
for TabbyAPI only.

Signed-off-by: kingbri <bdashore3@proton.me>
 2024-04-02 00:59:21 -04:00
Cohee a3ec0938c5 KoboldCpp grammar fix 2024-03-29 17:28:28 +02:00
Alexander Abushady 9bd3a526aa Fix for unique swipes 
Fix for unique swipes in Aphrodite
 2024-03-26 23:57:24 -04:00
50h100a 8b092adc14
Use mode enum to toggle dynatemp behavior. 2024-03-25 12:25:03 -04:00
Cohee df805d692b Fix some code 2024-03-24 21:42:27 +02:00
50h100a 6f7e7b85ab For Mancer: 
- Allow logprobs (works)
- Allow multiswipe (not yet)
- Adjust visible samplers
Fix: 0 logprob is 100% chance, handle accordingly.
 2024-03-24 14:45:37 -04:00
Cohee c8f84bd413 Textgen setting refactors 2024-03-19 01:38:55 +02:00
Cohee dc74f546d5
Merge pull request #1875 from kalomaze/cubic-curve 
smoothing_curve UI support
 2024-03-17 02:20:51 +02:00
Cohee a0279b636b Remove dead code 2024-03-08 08:41:54 +02:00
Cohee 2cdfda9d69 Actually use getCurrentDreamGenModelTokenizer 2024-03-08 08:40:03 +02:00
DreamGenX bc8d41b530 Implement suggestions 2024-03-07 17:28:38 +01:00
DreamGenX 5c410986a4 Add support for DreamGen API. 
API docs: https://dreamgen.com/docs/models/opus/v1
API keys: https://dreamgen.com/account/api-keys

I decided to base this on the text-completion API since it's more
flexible with SillyTavern's prompt formating capabilities.

This also means that custom context and instruct settings are required.

Will add documentation in a followup PR.
 2024-03-07 12:25:48 +01:00
Cohee 95c49029f7 Add aphrodite model selector 2024-03-01 23:02:43 +02:00
kalomaze 45776de1d5 Smoothing curve support for ooba 2024-03-01 00:06:34 -06:00
gabriel dhimoila 76669ff8bb add max_tokens_second 2024-02-29 00:55:25 +01:00
Cohee f962ad5c02 Add OpenRouter as a text completion source 2024-02-25 22:47:07 +02:00