NamH
d7f161f668
fix: scan the models folder recursive to find model metadata file ( #2982 )
...
Co-authored-by: James <james@jan.ai>
2024-06-04 10:14:11 +07:00
NamH
0a150b373c
chore: upgrade version model extension for hf auth token ( #2983 )
...
Co-authored-by: James <james@jan.ai>
2024-06-03 13:46:29 +07:00
NamH
02478b3242
feat: add input actions for setting item ( #2978 )
...
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-06-02 22:41:27 +07:00
NamH
4edef30e0e
feat: allow user to register their access token ( #2974 )
...
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-05-31 13:15:06 +07:00
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
Van Pham
9ac5696e35
chore/Bump-cortex-0.4.11 ( #2962 )
2024-05-29 17:57:41 +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
Van Pham
9cf9fa0dd3
Bump cortex to 0.4.9 ( #2940 )
2024-05-24 13:01:25 +07:00
Van Pham
f7c089c765
Bump cortex to 0.4.8 ( #2938 )
2024-05-22 21:21:02 +07:00
Hoang Ha
385ebb7750
Chore: phi3 long-context update ( #2936 )
...
* init
* init
* fix: correct version
* version bump
* correct url
* remove small
* correct size
2024-05-22 21:20:42 +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
e78d057f0f
fix: cortex process is not terminated properly ( #2921 )
...
* chore: bump cortex-cpp to 0.4.6
* Bump cortex 0.4.7
---------
Co-authored-by: Van Pham <64197333+Van-QA@users.noreply.github.com>
2024-05-18 14:14:56 +07:00
Louis
537ef20a54
chore: replace nitro by cortex-cpp ( #2912 )
2024-05-16 17:46:49 +07:00
Hoang Ha
218259945f
Chore: Add phi3 ( #2914 )
...
* init
* version bump
* fix: correct template
2024-05-16 14:58:21 +07:00
Louis
1130979008
fix: cohere stream param does not work ( #2907 )
2024-05-15 17:27:37 +07:00
Hoang Ha
eb7e96393b
add: gpt4o ( #2899 )
2024-05-14 14:16:12 +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
Henry
efbc96dad9
feat: inference anthropic extension ( #2885 )
...
* feat: implement inference anthropic extension
* chore: format style and correct typo of other extensions
2024-05-11 19:22:05 +07:00
Hoang Ha
2008aae100
Feat: Correct context length for models ( #2867 )
...
* fix: correct ctx
* version bump
* fix: correct ctxlen
* fix: correct ctxlen
* version bump
* fix: correct ctx + q4
* fix: correct ctxlen
* fix: correct ctx
* fix: correct ctx
* fix: correct ctx len
* fix: correct ctx
* fix: correct ctx
* fix: correct ctx
* fix: correct ctx
* fix: correct ctx
* fix: correct ctx
* fix: correct ctx
* fix: correct ctx
* version bump
2024-05-06 18:04:51 +07:00
Inchoker
d2266405cc
Add OpenRouter ( #2826 )
...
* Add OpenRouter
* fix cohere setting description
* fix: update to auto router
* fix: auto router
* add: config parameters
* fix: correct max tokens
---------
Co-authored-by: Jack Tri Le <Jack>
Co-authored-by: Hoang Ha <64120343+hahuyhoang411@users.noreply.github.com>
2024-05-06 17:36:52 +07:00
Henry
1e3e5a83f4
feat/implement-inference-martian-extension ( #2869 )
2024-05-06 15:24:07 +07:00
Henry
86fda1cf6c
feat: add model gpt-4 turbo ( #2836 )
...
* feat: add model gpt-4 turbo
* fix: correct naming
---------
Co-authored-by: Hoang Ha <64120343+hahuyhoang411@users.noreply.github.com>
2024-05-06 10:43:15 +07:00
Henry
4c88d03aa5
feat: add remote model command-r ( #2868 )
2024-05-06 10:37:57 +07:00
Hoang Ha
092a572684
Feat: Remote API Parameters Correction ( #2802 )
...
* fix: change to gpt4 turbo
* add: params
* fix: change to gpt 3.5 turbo
* delete: redundant
* fix: correct description
* version bump
* add: params
* fix: version bump
* delete: deprecated
* add: params
* add: new model
* chore: version bump
* fix: version correct
* add: params
* fix: version bump
* fix: change to gpt4 turbo
* add: params
* fix: change to gpt 3.5 turbo
* delete: redundant
* fix: correct description
* version bump
* add: params
* fix: version bump
* delete: deprecated
* add: params
* add: new model
* chore: version bump
* fix: version correct
* add: params
* fix: version bump
* fix: llama2 no longer supported
* fix: reverse mistral api
* fix: add params
* fix: mistral api redundant params
* fix: typo
* fix: typo
* fix: correct context length
* fix: remove stop
---------
Co-authored-by: Van Pham <64197333+Van-QA@users.noreply.github.com>
2024-05-04 15:44:19 +07:00
Louis
63a2f22414
Merge branch 'dev' into main
2024-04-25 14:14:54 +07:00
Hoang Ha
355ed9ff4f
Merge pull request #2812 from janhq/fix/model-version
...
Feat: Bump version
2024-04-24 22:48:29 +07:00
Hoang Ha
f9a8e06a4f
fix: version bump
2024-04-24 22:46:56 +07:00
Hoang Ha
eb3593e96a
fix: bump version
2024-04-24 22:24:22 +07:00
Hoang Ha
785b84d9ec
fix: bump version
2024-04-24 22:24:00 +07:00
Hoang Ha
ec589b1f22
fix: bump version
2024-04-24 22:23:40 +07:00
Hoang Ha
4d80f5c3c1
fix: bump version
2024-04-24 22:22:14 +07:00
Hoang Ha
984838a7bc
fix: bump version
2024-04-24 22:19:11 +07:00
Inchoker
96abd533c4
feat: cohere remote API extension ( #2785 )
...
* fix core
* add cohere extension
* add cohere response customizable
* nitpicking
* use transformResponse
* Update extensions/inference-cohere-extension/src/index.ts
Co-authored-by: Louis <louis@jan.ai>
* use prettier
* Update extensions/inference-cohere-extension/src/index.ts
Co-authored-by: Louis <louis@jan.ai>
* pass requestBody as object
* transformPayload as a property
* This is not correct. CHATBOT is an equivalent role to assistant.
system message should be used with the preamble parameter and should not be included in the chat_history
---------
Co-authored-by: Jack Tri Le <Jack>
Co-authored-by: Louis <louis@jan.ai>
2024-04-24 18:16:57 +07:00
Hoang Ha
68b0018d55
fix: version bump
2024-04-24 16:40:27 +07:00
Hoang Ha
e076c5ba4e
fix: remove featured
2024-04-24 16:38:47 +07:00
Hoang Ha
f5c4324f79
fix: remove featured
2024-04-24 16:38:30 +07:00
Hoang Ha
6bf12e42a8
fix: remove featured
2024-04-24 16:38:09 +07:00
Hoang Ha
3810b1a009
fix: remove featured
2024-04-24 16:37:48 +07:00
Hoang Ha
d14c3af99b
add: featured
2024-04-24 16:35:05 +07:00
Hoang Ha
3c294d6a48
Chore: Add phi-3 ( #2794 )
...
* add: phi-3
* chore: bump version
* fix: correct model id
2024-04-24 14:17:42 +07:00
Louis
da161cd159
fix: override cpu_threads setting from model.json ( #2789 )
2024-04-23 15:09:48 +07:00
Carsen Klock
f288a86647
Add new Llama 3 and models to Groq Extension ( #2786 )
2024-04-23 09:15:19 +07:00
NamH
97c15e6983
chore: detailed message when fetch invalid url ( #2780 )
...
Co-authored-by: James <james@jan.ai>
2024-04-22 21:42:31 +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
NamH
83e9e2b80a
chore: set default context length to 2048 ( #2776 )
...
Co-authored-by: James <james@jan.ai>
2024-04-22 19:57:00 +07:00
NamH
95632788e4
chore: default context length to 2048 ( #2746 )
2024-04-17 19:14:51 +07:00
NamH
a2cb1353cd
fix: cannot download phin34 model ( #2745 )
...
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-04-17 18:36:02 +07:00
Van Pham
e43ee8ec2c
Bump nitro to 0.3.22 ( #2740 )
...
* Bump nitro to 0.3.22
* Update model.json for Command-r-34b
Remove Coming Soon and Unavailable
2024-04-17 01:00:16 +07:00
NamH
31397de2d1
Refactor/deprecate hugging face ext ( #2620 )
...
* refactor: deprecate huggingface extension
Signed-off-by: James <james@jan.ai>
2024-04-16 17:23:45 +07:00
NamH
889d374fad
fix: log is not generated after clear log from setting ( #2732 )
...
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-04-15 22:53:04 +07:00
