Faisal Amir
|
dd308db17b
|
fix: auto select model when finished download from starter screen (#4083)
|
2024-11-22 12:52:37 +07:00 |
|
Louis
|
f709c7723f
|
fix: factory reset hang on wiping data
|
2024-11-21 23:10:48 +07:00 |
|
Louis
|
73007b49fa
|
chore: lint fix
|
2024-11-21 17:14:31 +07:00 |
|
Louis
|
f74994a735
|
fix: tensorrt-llm model list
|
2024-11-21 16:58:15 +07:00 |
|
Louis
|
55ad2f3931
|
fix: fix empty string in gpus_in_use settings to select the correct variant
|
2024-11-21 14:09:21 +07:00 |
|
Louis
|
8bd0f3da21
|
fix: inconsistent error handling
|
2024-11-19 23:18:52 +07:00 |
|
Louis
|
52c520d2c3
|
fix: app does not relaunch on Linux - add tests
|
2024-11-19 19:43:12 +07:00 |
|
Louis
|
28add39a51
|
chore: add model pull options - correct url path
|
2024-11-19 16:39:23 +07:00 |
|
Louis
|
363008d37f
|
fix: model import edge cases
|
2024-11-19 11:44:19 +07:00 |
|
Louis
|
7a084b6589
|
Merge pull request #4040 from janhq/fix/rerender-component
chore: refactor rerender components
|
2024-11-18 20:55:22 +07:00 |
|
Louis
|
5c5239097d
|
chore: update test
|
2024-11-18 19:53:03 +07:00 |
|
Louis
|
e9fd7f4554
|
fix: models load
|
2024-11-18 18:22:09 +07:00 |
|
Faisal Amir
|
b8e521164b
|
chore: remove conditional on dataloader
|
2024-11-18 16:48:27 +07:00 |
|
Faisal Amir
|
18e9a2e4d8
|
chore: remove get data on mount
|
2024-11-18 16:17:31 +07:00 |
|
Faisal Amir
|
a6f2de922c
|
chore: refactor rerender components
|
2024-11-18 16:10:57 +07:00 |
|
Louis
|
6f066357ed
|
chore: bump new engine version 0.1.39 and get rid of dangling process
|
2024-11-16 16:06:37 +07:00 |
|
Louis
|
3f6fb1561b
|
fix: remove cuda toolkit error message and bring back incremental model import
|
2024-11-12 12:10:26 +07:00 |
|
Louis
|
9530c695d3
|
chore: lint fix
|
2024-11-11 11:47:04 +07:00 |
|
Louis
|
19879ef279
|
fix: model import name and id is wrong on Windows
|
2024-11-11 10:30:22 +07:00 |
|
Louis
|
848f9c5eed
|
fix: migrate model settings and parameters but still allow model.yml editing
|
2024-11-09 12:54:06 +07:00 |
|
Louis
|
43d0e272ed
|
fix: should maintain legacy jan model parameters
|
2024-11-08 16:19:13 +07:00 |
|
Louis
|
9ddd26d952
|
chore: maintain model.json settings - cortex.cpp might extract a wrong prompt template
|
2024-11-08 15:50:15 +07:00 |
|
Louis
|
264720c71a
|
chore: support customized OpenAI model.json
|
2024-11-06 16:46:27 +07:00 |
|
Louis
|
964269dc46
|
fix: 3911 - inconsistent between download progress and model hub
|
2024-11-06 09:20:54 +07:00 |
|
Louis
|
d2fa38f081
|
test: correct tests
|
2024-11-05 08:33:58 +07:00 |
|
Louis
|
46d5faf59f
|
chore: new cortex-cpp binary - model import option and model size
|
2024-11-04 20:36:04 +07:00 |
|
Louis
|
b913af9f88
|
chore: model id is optional on import
|
2024-11-04 15:37:21 +07:00 |
|
Louis
|
a986c6de2d
|
chore: decide model name on pull and import
|
2024-11-04 15:37:20 +07:00 |
|
Louis
|
8c759676d9
|
chore: fix responsible issue when importing models (cortex.cpp does not support download in parallel yet)
|
2024-11-04 15:37:20 +07:00 |
|
Louis
|
1ab02b706f
|
fix: model import symlink
|
2024-11-04 15:37:19 +07:00 |
|
Louis
|
a466bbca38
|
chore: update legacy tensorrt-llm download and run
|
2024-11-04 15:37:19 +07:00 |
|
Louis
|
3643c8866e
|
fix: correct model settings on startup and strip down irrelevant model parameters
|
2024-11-04 15:37:18 +07:00 |
|
Louis
|
a0e2f16a3b
|
chore: binary naming convention - following llama.cpp release
|
2024-11-04 15:37:17 +07:00 |
|
Louis
|
6c0c2a00d6
|
test: fix getModels test case does not work with useDebounce
|
2024-11-04 15:37:17 +07:00 |
|
Louis
|
03333cc4c2
|
fix: onboarding should cover cortex models - debounce reduce model reload - rename cortex binary name
|
2024-11-04 15:37:17 +07:00 |
|
Louis
|
9afbfd609a
|
test: correct test cases
|
2024-11-04 15:37:16 +07:00 |
|
Louis
|
e8a9e8e28c
|
fix: inherits model decoration metadata from Jan
|
2024-11-04 15:37:16 +07:00 |
|
Louis
|
8ccbb56f95
|
chore: unload model on message error - so users can attempt to start
|
2024-11-04 15:37:16 +07:00 |
|
Louis
|
40957f7686
|
fix: model reload state - reduce model unload events emit
|
2024-11-04 15:37:15 +07:00 |
|
Louis
|
895c3d4246
|
fix: tests - useModels with remote models filter
|
2024-11-04 15:37:15 +07:00 |
|
Louis
|
8129c2319f
|
fix: downloaded models should account for remote models
|
2024-11-04 15:37:14 +07:00 |
|
Louis
|
ba59425e6a
|
fix: tests
|
2024-11-04 15:37:14 +07:00 |
|
Louis
|
03e15fb70f
|
feat: sync model hub and download progress from cortex.cpp
|
2024-11-04 15:37:14 +07:00 |
|
Louis
|
4080dc4b65
|
feat: model and cortex extensions update
|
2024-11-04 15:37:12 +07:00 |
|
Faisal Amir
|
5d628a2748
|
feat: save instruction for new threads as a stable feature (#3798)
|
2024-10-15 00:22:58 +07:00 |
|
Louis
|
87e1754e3a
|
chore: improve models and threads caching (#3744)
* chore: managing and maintaining models and threads in the cache
* test: add tests for hooks
|
2024-10-01 10:15:30 +07:00 |
|
Louis
|
ba1ddacde3
|
fix: correct model dropdown for local models (#3736)
* fix: correct model dropdown for local models
* fix: clean unused import
* test: add Model.atom and model.Engine tests
|
2024-09-30 11:58:55 +07:00 |
|
Louis
|
8334076047
|
fix: #3491 - Unable to use tensorrt-llm (#3741)
* fix: #3491 - Unable to use tensorrt-llm
* fix: abortModelDownload input type
|
2024-09-30 11:58:46 +07:00 |
|
Louis
|
36c1306390
|
fix: #3515 - The default assistant instructions are ignored (#3721)
|
2024-09-24 10:40:45 +07:00 |
|
Louis
|
302b73ae73
|
test: add web helpers, services, utils tests (#3669)
* test: add web helpers tests
* fix: coverage report
* test: add more tests
* test: add more generated tests
* chore: add more tests
* test: add more tests
|
2024-09-20 14:24:51 +07:00 |
|