13 Commits

Author SHA1 Message Date
Hoang Ha
bd5a0ea8ab
Chore: Model Hub update (#2966)
* fix: correct size

* version bump

* add: codestral 22b

* add: codestral 22b

* versino bump

* upgrade to v3

* Update stop token default-model.json 

confirmed with Rex

* fix: whitespace

---------

Co-authored-by: Van Pham <64197333+Van-QA@users.noreply.github.com>
2024-05-30 12:33:47 +07:00
Hoang Ha
25daba9696
Chore: aya update (#2941)
* init

* init

* fix: correct format

* version bump

* add: aya 8b, aya 35b, phi3

* fix: stop token

* fix: stop token
2024-05-24 18:10:23 +07:00
Hoang Ha
65b8d8e66b
Fix: Phi-3 doesn't display (#2928)
* fix: params correction

* add phi

* version bump
2024-05-20 23:45:06 +07:00
Louis
537ef20a54
chore: replace nitro by cortex-cpp (#2912) 2024-05-16 17:46:49 +07:00
Hoang Ha
1e0d4f3753
Feat: Adjust model hub v0.4.13 (#2879)
* fix: correct phi3

* redundant phi2 dolphin

* add: hermes llama3

* add: ngl settings

* correct ctx len

* correct ngl

* correct maxlen + ngl

* disable phi3

* add ngl

* add ngl

* add ngl

* add ngl

* add ngl

* add ngl

* add ngl

* remove redundant  hermes pro

* add ngl

* add ngl

* add ngl

* remove miqu

* add ngl

* add ngl

* add ngl

* add ngl

* remove redundant

* add ngl

* add ngl

* add ngl

* add ngl

* add ngl

* add ngl

* add ngl

* add ngl

* add ngl

* version package bump

* feat: resolve issue of cannot found model in the extensions due to the removal

* feat: completely remove hermes-pro-7b

* feat: completely remove openhermes-neural-7b and miqu-70b, and add llama3-hermes-8b via renaming from Rex

* fix: correct description

---------

Co-authored-by: Van-QA <van@jan.ai>
2024-05-13 11:48:03 +07:00
Van Pham
67db45ff3c
chore: add model.json for Llama3 and other outdated model version (#2773)
* chore: add model.json for Llama3 and other outdated model version

* fix: consistency format

* fix: correct folder id

* update: bump version

* add: stop words

* fix: model.json

* Update extensions/inference-nitro-extension/resources/models/llama3-8b-instruct/model.json

* Update extensions/inference-nitro-extension/resources/models/llama3-8b-instruct/model.json

Based on suggested change

Co-authored-by: Nikolaus Kühn <nikolaus.kuehn@commercetools.com>

---------

Co-authored-by: Van-QA <van@jan.ai>
Co-authored-by: Hoang Ha <64120343+hahuyhoang411@users.noreply.github.com>
Co-authored-by: Louis <louis@jan.ai>
Co-authored-by: Nikolaus Kühn <nikolaus.kuehn@commercetools.com>
2024-04-22 21:40:22 +07:00
Louis
d93d74c86b
feat: nitro additional dependencies (#2674) 2024-04-11 09:13:02 +07:00
NamH
e0d6049d66
chore: extension should register its own models (#2601)
* chore: extension should register its own models

Signed-off-by: James <james@jan.ai>

---------

Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-04-05 14:18:58 +07:00
NamH
fa35aa6e14
feat: dynamically register extension settings (#2494)
* feat: add extesion settings

Signed-off-by: James <james@jan.ai>

---------

Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
Co-authored-by: Louis <louis@jan.ai>
2024-03-29 15:44:46 +07:00
Louis
ff7ec39915
fix: incompatible browser dependency (#2439)
* fix: incompatible browser dependency

* fix: update model extension to use rollup

* fix: test timeout
2024-03-21 16:54:42 +07:00
Louis
3412a23654
chore: prettier fix (#2019) 2024-02-15 08:38:05 +07:00
NamH
9e1c41b897
fix: chat using web interface (#1889)
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-02-02 10:45:10 +07:00
Louis
f4f861d0e9
refactor: introduce node module in nitro extension (#1630) 2024-01-17 11:28:54 +07:00