ba91845ced
Merge pull request #3090 from kallewoof/202411-auto-templates
...
Derived templates
2024-11-23 17:56:18 +02:00
803b7fca89
Remove custom header
2024-11-23 17:50:32 +02:00
3c2e802547
Validate instruct/context existance
2024-11-23 17:44:23 +02:00
c8e6ba4d7f
Add template hash for gemma-2-2b
2024-11-23 17:38:12 +02:00
362bdf0c46
Don't log when no endpoint available. Remove pointless header
2024-11-23 17:32:12 +02:00
b9cc763d51
Fix typo in file name
2024-11-23 17:30:50 +02:00
eccd1ab381
Exclude 'derived' from instruct templates
2024-11-23 16:06:10 +02:00
049ae541aa
Add 'node:' prefix to import
2024-11-23 16:03:13 +02:00
2e661c36e5
Check for response ok
2024-11-23 16:01:14 +02:00
50922c11fa
Change icon for derivation
2024-11-23 16:01:05 +02:00
8ed6439da2
Update documentation links
2024-11-23 15:57:22 +02:00
876da6899d
Merge branch 'staging' into 202411-auto-templates
2024-11-23 15:47:11 +02:00
7cd68d827b
Merge pull request #3098 from tincansimagine/for18n
...
feat: Improve Korean data-i18n
2024-11-23 15:45:55 +02:00
c5bd43405c
Alias /note-pos command to match /inject
2024-11-23 15:34:08 +02:00
3af5302714
Merge pull request #3103 from Finadil/staging
...
Add author's note STscript returns, role changing, and aliases
2024-11-23 15:29:01 +02:00
446146674c
Add STscript returns, role changing, and aliases
...
Adds the following STscript changes:
-Returns to all commands and makes arguments optional
-before_scenario option for chat insertion position (to match UI)
-/note-role to change the chat insertion role
-/note- Aliases to all commands so they're centralized
2024-11-23 06:49:30 -05:00
dedc10b412
feat: imporve Korean data-i18n
2024-11-23 20:43:16 +09:00
90ee0398f2
Merge pull request #3100 from tincansimagine/new-model-pr
...
feat: Add multiple delayed model updates
2024-11-22 19:56:32 +02:00
ecbf9df79a
Update context sizes for new Cohere models
2024-11-22 17:54:03 +00:00
85ca08a2ea
Settings for new gemini
2024-11-22 17:50:33 +00:00
1938e8ac14
Remove to-int conversion from Novel logprobs
2024-11-22 17:46:20 +00:00
6ae120900d
Support images in custom prompt post-processing
2024-11-22 17:39:49 +00:00
8688079882
feat: Add multiple delayed model updates
2024-11-22 14:44:54 +09:00
9a15f45a2c
feat: Improve Korean data-18n
2024-11-22 08:08:05 +09:00
3789381c6c
added substr derivations with one example
2024-11-21 13:14:33 +09:00
c30dde8471
rename /chat_template to /props, and switch to non-trimmed hashes
2024-11-21 11:38:57 +09:00
4214c9d894
trim chat template before hashing
2024-11-20 15:12:42 +09:00
50ffaeb06a
UI: add UI to enable/disable auto-derived templates
2024-11-20 13:28:17 +09:00
bb062f5ec9
update endpoint to reflect koboldcpp update
2024-11-20 13:11:51 +09:00
56137d2b57
Merge pull request #3093 from WolframRavenwolf/Mistral-2411
...
Mistral-2411 context+instruct presets
2024-11-19 22:32:56 +02:00
5d2858268e
Mistral-2411 -> Mistral V7
2024-11-19 21:12:01 +01:00
30269e8ec6
Mistral-2411 context+instruct presets
2024-11-19 20:10:10 +01:00
99220d6a88
Groups: add 'manual' reply strategy
2024-11-19 20:48:43 +02:00
c3b416b4cf
Claude: fix prefill tool calling hack with at-depth caching
2024-11-19 20:48:02 +02:00
feb1b91619
template derivation: add support for llama.cpp server backend
2024-11-19 23:38:38 +09:00
cdc0147490
fix error console.log message
2024-11-19 21:41:57 +09:00
c2eaae3d42
switch to crypto lib
2024-11-19 21:39:35 +09:00
f25ea9f6d6
template derivation: move hash part to backend
2024-11-19 20:09:29 +09:00
0e2fdf37a8
feature: derived templates
...
This PR adds a simple hash based method for picking context and instruct templates based on the chat template, when provided by the back end.
2024-11-19 17:27:25 +09:00
67869364a5
ImageGen: add BFL API for image generation
2024-11-19 00:30:28 +02:00
54db4983f4
Merge pull request #3085 from honey-tree/claude-caching-at-depth
...
Claude caching at depth
2024-11-18 21:31:12 +02:00
3b03f07ebf
[chore] eslint fixes
2024-11-18 21:29:56 +02:00
c3483bc432
Merge branch 'staging' into claude-caching-at-depth
2024-11-18 21:03:33 +02:00
dde9f93d77
Merge pull request #3088 from ceruleandeep/feature/comfyGgufModels
...
Feature/comfy gguf models
2024-11-18 20:52:52 +02:00
5478b37b22
Don't use deprecated fetch method.
2024-11-18 20:39:44 +02:00
b2b5c1f10c
ComfyUI: Log error details on prompt submission
2024-11-18 20:35:48 +02:00
87f2a9e630
Merge branch 'staging' into feature/comfyGgufModels
2024-11-18 20:10:51 +02:00
4c0da00f5b
Update OpenRouter providers listing
...
Closes #3089
2024-11-18 20:09:56 +02:00
b651d31780
MistralAI: new pixtral large model
2024-11-18 16:10:20 +00:00
378dfd3626
Vectors: escape file names
2024-11-18 15:24:26 +00:00
Cohee
Finadil
tincansimagine
Karl-Johan Alm
Wolfram Ravenwolf