Hoang Ha
1e02cdeae7
add: tinyllama
2024-04-01 10:27:22 +07:00
Hoang Ha
daf4dcadd3
fix: correct hermes pro author
2024-03-27 21:36:22 +07:00
hahuyhoang411
51c6836cdc
fix: gemma
2024-03-27 18:23:11 +07:00
hahuyhoang411
9f43a6348b
fix: gemma 7b better description
2024-03-27 18:23:11 +07:00
hahuyhoang411
23eb53ace5
add: hermes pro better version of openhermes
2024-03-27 18:23:11 +07:00
hahuyhoang411
8c2273037f
fix: small adjust stable zephyr
2024-03-27 18:23:11 +07:00
hahuyhoang411
09a7e4ec2a
add: mistral 70b leak
2024-03-27 18:23:11 +07:00
hahuyhoang411
ef3ff2cdc3
fix: update description for stable zephyr 3b
2024-03-27 18:23:11 +07:00
hahuyhoang411
c09e273b87
delete: starling 7b redundant
2024-03-27 18:23:11 +07:00
hahuyhoang411
5929fa8687
delete: merlinite 7b low performance
2024-03-27 18:23:11 +07:00
hahuyhoang411
209a97a79a
delete: redundant solar 10B
2024-03-27 18:23:11 +07:00
hahuyhoang411
5b9549b0f9
delete: redundant capybara 34b
2024-03-27 18:23:11 +07:00
hahuyhoang411
7063300a34
delete: dolphin mixtral due to the low performance
2024-03-27 18:23:11 +07:00
hahuyhoang411
faa991331f
fix: change the folder id of llama 7b for consistancy
2024-03-27 18:23:11 +07:00
hahuyhoang411
316db44a56
fix: change the folder id of llama 70b for consistancy
2024-03-27 18:23:11 +07:00
hahuyhoang411
ebcd5ff8e9
fix: change the folder id of llava 13b for consistancy
2024-03-27 18:23:11 +07:00
hahuyhoang411
a0a02cdd1d
fix: change the folder id of mistral 7b for consistancy
2024-03-27 18:23:11 +07:00
hahuyhoang411
2621dc7590
fix: change the folder id of llava for consistancy
2024-03-27 18:23:11 +07:00
hahuyhoang411
811271b288
update: llava to 1.6 version
2024-03-27 18:23:11 +07:00
hahuyhoang411
9b76783916
fix: change folder id of mistral 7b for consistancy
2024-03-27 18:23:11 +07:00
hahuyhoang411
ca15a6bf28
update: noromaid version to 0.4
2024-03-27 18:23:11 +07:00
hahuyhoang411
2384706989
update: openchat description
2024-03-27 18:23:11 +07:00
hahuyhoang411
2456628023
update: phind 34b description and change to q4
2024-03-27 18:23:11 +07:00
hahuyhoang411
4762ab1ca9
fix: change folder id of stealth for consistancy
2024-03-27 18:23:11 +07:00
hahuyhoang411
90bd223af5
delete: tinyllama 1.1b
2024-03-27 18:23:11 +07:00
hahuyhoang411
5b0b0c5c1f
fix: trinity image to new folder
2024-03-27 18:23:11 +07:00
hahuyhoang411
d3e014b5c7
fix: change folder id of trinity for consistancy
2024-03-27 18:23:11 +07:00
hahuyhoang411
c0b6040f1c
fix: change yi 34B from q4 to q5
2024-03-27 18:23:11 +07:00
hahuyhoang411
75cf3e0ad1
delete: tulu 70b
2024-03-27 18:23:11 +07:00
hahuyhoang411
6c9ebc8f25
delete: phi-2
2024-03-27 18:23:11 +07:00
hahuyhoang411
002e74d702
fix: alternative to phi-2
2024-03-27 18:23:11 +07:00
hahuyhoang411
f7b628a035
fix: correct the system message for vistral
2024-03-27 18:23:11 +07:00
hahuyhoang411
18a6ee2efd
add: vistral 7b - vietnamese llm
2024-03-27 18:23:11 +07:00
hahuyhoang411
c9a73f887f
fix: typo
2024-03-27 18:23:11 +07:00
hahuyhoang411
46a0dd8c35
add: ibm merlinite 7b
2024-03-27 18:23:11 +07:00
hahuyhoang411
88e96cd686
add: command-r cohereai model for rag
2024-03-27 18:23:11 +07:00
Louis
7857a6e75e
fix: upload document mid-thread does not work ( #2504 )
2024-03-26 22:22:54 +07:00
Louis
acbec78dbf
fix: refactor inference engines to extends AIEngine ( #2347 )
...
* fix: refactor nitro to extends localoaiengine
* fix: refactor openai extension
* chore: refactor groq extension
* chore: refactor triton tensorrt extension
* chore: add tests
* chore: refactor engines
2024-03-22 09:35:14 +07:00
Meta Spartan
0348aa3321
feat: Groq Inference Extension ( #2263 )
...
* feat: Groq Inference Extension
* Add Groq supported models
* Fix folder typo
* Add Groq options to interface and new API Key saving, tested working
* Fix linting
2024-03-18 06:40:20 +07:00
Hoang Ha
610a384af8
Chore: Update new models to model hub ( #2192 )
...
* add: qwen 7B
* add: gemma 7B
* add: qwen prompt tempalte
* fix: prompt template gemma 7b
* add: gemma 2b
* fix: correct id gemma 2b
* chore: fix noromaid model size
2024-03-06 21:28:05 +07:00
hiro
e6c10202e0
feat: Jan can see ( #2069 )
...
* feat: jan can see
feat: Add GPT-4 Vision model (Preview)
fix: Add visionModel as property in ModelInfo
fix: Fix condition to load local messages in useSetActiveThread hook
feat: Enable Image as input for chat
fix: Update model parameters in JSON files for remote GPT models
fix: Add thread as optional
fix: Add support for message as image
fix: Linter
fix: Update proxyModel to proxy_model and add textModel
chore: Change proxyModel to proxy_model
fix: Update settings with visionModel and textModel
fix: vision model passed through the retrieval tool
fix: linter
* fix: could not load image and request is not able to be sent
---------
Co-authored-by: Louis <louis@jan.ai>
2024-03-05 08:33:09 +07:00
Louis
53006dd26e
fix: broken model.json update ( #2099 )
2024-02-19 22:07:12 +07:00
Hoang Ha
3af0ae1481
Merge pull request #1829 from janhq/chore/update-hub
...
chore: update models
2024-02-19 10:25:09 +07:00
hahuyhoang411
f7a3c921fd
fix(dolphin phi2): resolved conflict
2024-02-19 09:56:44 +07:00
hahuyhoang411
2b0bc9f790
update(openchat-3.5): pump to the latest version
2024-02-19 09:54:41 +07:00
Louis
3ea8c6071c
fix: check for updates should show no update are availale on the latest build ( #2075 )
2024-02-18 20:55:31 +07:00
Louis
eb09399fbf
chore: reduce bundle size ( #1970 )
...
* chore: reduce bundle size
* chore: trimming langchainjs
* chore: trim pdf-parse
2024-02-09 19:23:56 +07:00
Hoang Ha
24dd13a305
fix(dolphin-phi): redundant of new lines character
2024-02-05 11:20:49 +07:00
hahuyhoang411
8d81c7eb41
fix(stable zephyr): update description
2024-02-03 13:51:01 +07:00
hahuyhoang411
25d7c6a0b5
add(llamacorn): correct tags
2024-02-03 13:51:01 +07:00
