181 Commits
Author SHA1 Message Date
Zuellni e98048093c Fix typo in js script, add printing to console for preview node, remove deprecated config option 2024-12-06 15:22:11 +01:00
Zuellni 63c7394d2c Merge pull request #27 from ricklove/main
FIX Major Performance problem on prompt
2024-09-22 08:44:30 +02:00
Rick Love fbbe8bc910 FIX serious performance issue on every prompt 2024-09-21 21:29:02 -05:00
Zuellni bef6a0d3cb Fix default values not showing in preview 2024-08-23 22:21:47 +02:00
Zuellni 97ec4b551c Update README.md 2024-08-07 20:06:26 +02:00
Zuellni 9f9d25dd49 Rename the convert node, some fixes and cleanup 2024-08-04 12:57:22 +02:00
Zuellni 4d58d29f8e Fix attention size typo 2024-07-31 01:25:02 +02:00
Zuellni 5c63d0609f Remove the hidden inputs since they don't seem to be working anyway (no prompt in workflow), touch-up the convert node a bit 2024-07-29 19:22:39 +02:00
Zuellni 1b02390317 Update workflow 2024-07-29 16:53:02 +02:00
Zuellni 42d621d4fd Merge pull request #25 from Zuellni/dev
Overhaul
2024-07-29 16:52:19 +02:00
Zuellni 66a538e316 Update README.md 2024-07-29 15:51:34 +02:00
Zuellni 2db2d93844 Added a convert node, a string node and fixed some js (probably) 2024-07-29 15:41:49 +02:00
Zuellni 2acc730ad3 Update README.md 2024-07-28 21:31:21 +02:00
Zuellni 7ae7ef9a24 Split some nodes, added a format node that uses tokenizer config template 2024-07-28 17:33:07 +02:00
Zuellni 8311351697 Cache should be a multiple of 256 for paged attention 2024-06-26 16:01:08 +02:00
Zuellni d5feb5a293 Clean up cache 2024-06-26 13:07:37 +02:00
Zuellni 0bd03f4dae Clean up imports 2024-06-24 12:33:30 +02:00
Zuellni cc6c50e2ff Merge pull request #23 from Zuellni/dev
Switch to dynamic generator, bump minimum exllamav2 version
2024-06-14 18:52:24 +02:00
Zuellni 5a90464b6c Update README.md 2024-06-14 18:48:05 +02:00
Zuellni 51728c0102 Update requirements.txt 2024-06-14 13:28:48 +02:00
Zuellni cac9d1fdf4 Update README.md 2024-06-14 13:24:38 +02:00
Zuellni f54093078e Clean up README 2024-06-14 13:21:42 +02:00
Zuellni add411a7c3 Merge remote-tracking branch 'origin/main' into dev 2024-06-14 13:15:47 +02:00
Zuellni 49ace07a0e Update README.md 2024-06-14 12:51:36 +02:00
Zuellni 4754f78c70 Add option to enable/disable flash attention and fast tensors 2024-06-14 11:50:22 +02:00
Zuellni f988703614 Add custom stop conditions 2024-06-14 11:33:10 +02:00
Zuellni e91a1ce2c6 Switch to dynamic generator 2024-06-14 10:57:28 +02:00
Zuellni e5e13c40ed Update README.md 2024-06-05 09:53:12 +02:00
Zuellni d7413b2ebc Fix vram usage with higher context 2024-05-17 22:55:50 +02:00
Zuellni c005e3c637 Update config init 2024-05-04 09:13:01 +02:00
Zuellni 4422f0b0d0 Update readme 2024-04-22 18:30:33 +02:00
Zuellni 4633de563a Update workflow with llama-3 format 2024-04-22 16:18:18 +02:00
Zuellni 87810044ea Change default cache bits to 16, reorganize imports, update readme 2024-04-22 15:50:50 +02:00
Zuellni 8c2f17829a Clarify instructions 2024-04-08 03:03:53 +02:00
Zuellni c5765ffb8c Update with a cascade workflow 2024-04-07 20:19:55 +02:00
Zuellni fb7b7ff683 Update readme 2024-04-07 20:00:44 +02:00
Zuellni fb5b6d95ef Update link 2024-04-07 19:55:34 +02:00
Zuellni d2543cbd59 Simplify instructions 2024-04-07 19:52:53 +02:00
Zuellni baed69aba5 Bump minimum exllamav2 version, add autosplit and q4 cache, some reformatting 2024-04-07 19:35:32 +02:00
Zuellni d2b4d7a796 More sanity checks for model unloading, bump exllama 2024-02-26 13:24:03 +01:00
Zuellni f7a108315e Update readme 2024-02-21 23:06:35 +01:00
Zuellni 217304e0ef Only unload other models if unload is checked 2024-02-17 16:53:00 +01:00
Zuellni 8c4b9d058f Update workflow 2024-02-17 15:14:46 +01:00
Zuellni 861aa6fc51 Update readme 2024-02-17 15:13:53 +01:00
Zuellni 8b7b957b3e Add gc again 2024-02-17 14:53:54 +01:00
Zuellni e1c8e61291 Unload other models first before loading llms, rename some params, update requirements 2024-02-17 14:40:46 +01:00
Zuellni ca41704f38 Update readme 2024-02-14 20:26:46 +01:00
Zuellni bf64bcc0e4 Split requirements to file, neutralize samplers by default 2024-02-14 20:23:27 +01:00
Zuellni 9ffbacf080 Update requirements 2024-02-12 16:38:52 +01:00
Zuellni 6cc728d7cb Update readme 2024-02-09 16:13:30 +01:00