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
Louis
0e48be67e8
feat: support multiple model binaries ( #1659 )
...
* feat: Support multiple model binaries
* fix: Update downloadModel with multiple binaries handler
* feat: Add 3 models with multiple binaries
* chore: fix model download
* fix: model file lookup & model path
* chore: add .prettierrc
* chore: refactor docs
* chore: bump model version
* fix(capybara): add filename
* fix(codeninja): add file name + llama model path
* fix(default): add llama model path
* fix(deepseek coder): add filename
* fix(deepseek 33B): add filename
* fix(dolphin mixtral): add filename
* fix(llama2-chat): add filename
* fix(llama2-70B): add filename
* fix(mistral 7b): add filename + model path
* fix(bakllava): correct size model
* fix(llava-7b): correct size model
* fix(llava-13b): correct size model
* fix(mixtral-8x7b): add file name + modelpath
* fix(noramaid-7b): add file name + modelpath
* fix(openchat-7b): add file name + modelpath
* fix(openhermes-7b): add file name + modelpath
* fix(phi2-3b): add file name + modelpath
* fix(phind): add file name + modelpath
* fix(solarslerp): add file name + modelpath
* fix(starling): add file name + modelpath
* fix(stealth): add file name + modelpath
* fix(tinyllama): add file name + modelpath
* fix(trinity): add file name + modelpath
* fix(tulu): add file name + modelpath
* fix(wizardcoder): add file name + modelpath
* fix(yi): add file name + modelpath
* update from source -> sources
Signed-off-by: James <james@jan.ai>
---------
Signed-off-by: James <james@jan.ai>
Co-authored-by: hiro <vuonghoainam.work@gmail.com>
Co-authored-by: hahuyhoang411 <hahuyhoanghhh41@gmail.com>
Co-authored-by: James <james@jan.ai>
2024-01-25 14:05:33 +07:00
NamH
666bc01e89
fix(Model): #1662 imported model does not use gpu ( #1723 )
...
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-01-23 13:40:50 +07:00
Louis
f025f111cc
chore: typo model.json ( #1599 )
2024-01-15 15:50:20 +07:00
Louis
19153c4137
fix: stop word update ( #1457 )
...
* fix: stop word update
* fix: enable stop settings
---------
Co-authored-by: hahuyhoang411 <hahuyhoanghhh41@gmail.com>
2024-01-11 10:03:59 +07:00
Hoang Ha
0dd12950df
fix(magicoder): correct the id and update parameters ( #1448 )
...
fix(capybara): change description + parameters
fix(codeninja): update description + add parameters
delete(magicoder): this model is failed to load due to gguf
fix(deepseek-1.3b): update description + add parameters
fix(deepseek-34b): update description + add parameters
fix(dolphin8x7b): update description + parameters
fix(llama2-chat-7b): update description + add parameters
fix(llama2-chat-70b): update description + add parameters
fix(mistral-7b): update description + add parameters
fix(mistral): degrade to v0.1 due to giberish output from v0.2
fix(mixtral): update desciption + parameters
fix(noromaid): update description + parameters
fix(mistral7b): correct the prompt template
update(openchat): add parameters
fix(openhermesneural): update parameter + description
fix(openhermesneural): update max_tokens
delete(pandora): remove pandora
fix(phi2): update parameter
update(phind34b): update description + change to q4 + add parameter
update(solar-slerp): update parameter
fix(starling): update description + parameter
fix(openchat): add to recommended
fix(stealth): add parameters
fix(tinyllama): update description + parameters
fix(trinity): update description + parameters
fix(tulu2): update description + parameters
fix(stealth): change max_tokens to 4096
update(wizardcoder): update parameter + description
update(wizardcoder): update description
update(wizardcoder): change to q4
fix(yarn-mistral): update parameters
fix(yarn-mistral): change to q4
update(wizardcoder): correct the size of q4 model
fix(model-extension): pump to 1.0.20
fix(tinyllama): change to q8
fix(phi-2): change to q8
fix(deepseek34b): change to q4
fix(mistral7b): update the stop token
fix(starling): remove recommended
2024-01-08 23:00:01 +07:00
Hoang Ha
7f4be92700
Update model hub ( #1383 )
...
* fix(openchat): remove from featured model
* fix(model-extension): update to version 1.0.19
* fix(openchat): fix typo
2024-01-05 15:32:30 +07:00
NamH
764e4c6fe3
fix(Model): remove unsupported default model setting params ( #1382 )
...
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-01-05 15:13:21 +07:00
hahuyhoang411
61cddcb7e5
fix(stealth): add to featured model
2024-01-05 14:42:13 +07:00
hahuyhoang411
9160c718d6
fix(trinity): update cover path for trinity v1.2
2024-01-05 14:38:14 +07:00
Hoang Ha
84a09ae03f
Chore/update model hub ( #1342 )
...
* fix(mistral-ins): clean redundant parameters
* add(yarn-mistral): update new requested model
* fix(trinity-v1): delete trinity v1 from the hub
* add(tulu-2-70b): llama 70b alternative
* fix(lzlv-70b): delete lzlv-70b and changed to tulu-2
* fix(mistral-ins): upgrade model version to v0.2
* fix(model-extention): pump version to 1.0.18
* add(dolphin 8x7b): update the current best moe finetuned model
* add(openchat): the best 7b model
* fix(tinyllama): pump version of the model to v1
* fix(stealth): upgrade stealth to v1.3
* Revert "fix(stealth): upgrade stealth to v1.3"
This reverts commit da24df3fb5d69f93d92cc4dd45f991d548aff6aa.
* fix(stealth): upgrade version to v1.3
2024-01-05 13:50:35 +07:00
NamH
26eb1d9a67
feat(Model): #1028 made model.json optional ( #1314 )
...
* feat(Model): #1028 made model.json optional
Signed-off-by: James <james@jan.ai>
---------
Signed-off-by: James <james@jan.ai>
Co-authored-by: James <james@jan.ai>
2024-01-04 16:50:32 +07:00
hahuyhoang411
eb463e68c0
fix(codeninja): update the description
2023-12-29 16:25:03 +07:00
hahuyhoang411
281e1cd2ce
fix(stealth): delete state and update to v1.2
2023-12-28 18:41:18 +07:00
hahuyhoang411
4e5297bebc
add(codeninja): add new top coding model
2023-12-26 21:30:26 +07:00
hahuyhoang411
0dd6e935aa
add(magiccoder): add new model magiccoder 7b due to users requested
2023-12-26 17:21:41 +07:00
hahuyhoang411
6e94e11c6c
fix(trinity-v1): add a notification for users to use trinity v1.2
2023-12-26 17:16:06 +07:00
hahuyhoang411
3909fe47ff
add(stealth): add new model to the list
2023-12-26 17:15:08 +07:00
hahuyhoang411
803e89e644
fix(mixtral): change the tag to 70B
2023-12-21 20:56:59 +07:00
hahuyhoang411
206bb7c271
fix(solar): change tag to 13b
2023-12-21 20:56:13 +07:00
hahuyhoang411
c35bdb2f25
fix(pandora): change tag to 13b
2023-12-21 20:54:02 +07:00
hahuyhoang411
1e3a732b9b
fix(pandora-v1): change prompt template
2023-12-21 20:45:28 +07:00
hahuyhoang411
d5677a180a
fix(trinity-v1): change prompt template
2023-12-21 20:45:00 +07:00
hahuyhoang411
7bb179732c
fix(trinity-v1): remove featured tag
2023-12-21 13:45:00 +07:00
hahuyhoang411
36d8b331a7
fix(trinity-v1.2): update thename into v1.2
2023-12-21 13:43:02 +07:00
hahuyhoang411
996f5af6d2
fix(trinity-v1): add it back for potential bug
2023-12-21 13:42:13 +07:00
hahuyhoang411
bac4191094
fix(phi2): update correct model size
2023-12-21 13:07:15 +07:00
hahuyhoang411
aa623bf608
fix(phi2): update the right prompt template
2023-12-21 11:52:14 +07:00
hahuyhoang411
fd6a87ecb3
fix(trinity): change trinity folder to v1.2
2023-12-21 11:50:53 +07:00
hahuyhoang411
42e60daee1
fix(trinity): update trinity version to v1.2
2023-12-21 11:49:10 +07:00
hahuyhoang411
762aa4e405
fix(pandora): change pandora tags to merged
2023-12-21 11:45:57 +07:00
hahuyhoang411
f182bb2f3a
add(model): add phi-2, fix noromaid, delete solar, fix pandora
2023-12-21 11:45:04 +07:00
hahuyhoang411
beb01afb9b
fix(gpt): update model version
2023-12-19 11:15:29 +07:00
hahuyhoang411
a09a486906
fix(tinyllama): adjust ctx+maxtok
2023-12-15 16:36:39 +07:00
hahuyhoang411
2d63efdd86
fix(models): update ctxlen + maxlength to 4096
2023-12-15 16:35:00 +07:00
Hoang Ha
4c9a26474b
Hotfix model hub ( #1033 )
...
* add(openhermes): hotfix cover png
* add(openhermes): hotfix tag
* add(solarslerp): update missing model.json
2023-12-15 16:24:41 +07:00
Hoang Ha
ecc866427b
Update Model.json ( #1005 )
...
* add(mixtral): add model.json for mixtral
* archived some models + update the model.json
* add(model): add pandora 10.7b
* fix(model): update description
* fix(model): pump vers and change the featured model to trinity
* fix(model): archive neuralchat
* fix(model): decapriated all old models
* fix(trinity): add cover image and change description
* fix(trinity): update cover png
* add(pandora): cover image
* fix(pandora): cover image
* add(mixtral): add model.json for mixtral
* archived some models + update the model.json
* add(model): add pandora 10.7b
* fix(model): update description
* fix(model): pump vers and change the featured model to trinity
* fix(model): archive neuralchat
* fix(model): decapriated all old models
* fix(trinity): add cover image and change description
* fix(trinity): update cover png
* add(pandora): cover image
* fix(pandora): cover image
* chore: model desc nits
* fix(models): adjust the size for solars and pandoras
* add(mixtral): description
---------
Co-authored-by: 0xSage <n@pragmatic.vc>
2023-12-15 14:19:49 +07:00
hahuyhoang411
a784bf0114
fix(model.json): update new prompt_template
2023-12-13 14:25:40 +07:00
hiro
97f3733a52
chore: remove default parameters for openai gpt models
2023-12-10 20:16:37 +07:00
Louis
ef9dfc9cce
chore: add ready state to remote models
2023-12-08 23:07:30 +07:00
hiro
6cd4cb95fe
fix: model gpt json
2023-12-08 23:06:49 +07:00
hiro
2a853a23ea
feat: Add openai models
2023-12-08 23:06:49 +07:00
hiro
28368ee03b
fix: Add engine nitro
2023-12-08 23:06:49 +07:00
hiro
6add24c643
fix: debugging
2023-12-08 23:06:49 +07:00
hiro
06ca4142bf
fix: Change model folder name for openai gpt-3.5-turbo
2023-12-08 23:06:49 +07:00
hiro
05b9a7bfc9
fix: Delete default oai gpt 3.5 settings
2023-12-08 23:06:49 +07:00
hiro
750f09cc81
fix: update engine field in tiny llama 1.1b
2023-12-08 23:06:49 +07:00
hiro
22f12cd02c
fix: Update model.json for Hub with engine nitro/ openai
2023-12-08 23:06:49 +07:00
hiro
5f8e2ae54c
fix: Add engine llama.cpp to local models
2023-12-08 23:06:08 +07:00
