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
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
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
hahuyhoang411
a784bf0114
fix(model.json): update new prompt_template
2023-12-13 14:25:40 +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
hahuyhoang411
ff69e4fe51
update models
2023-12-04 17:33:26 +07:00
hahuyhoang411
69af5a034a
update tags
2023-12-04 16:38:13 +07:00
hahuyhoang411
7017e6426d
update name for models
2023-12-04 16:22:42 +07:00
hahuyhoang411
c27a1cc379
update tags for models
2023-12-04 11:56:39 +07:00
Hoang Ha
e6812b1247
chore: pre-populate Jan's /models folder with model.jsons ( #775 )
...
* draft model.json
* islm3b update
* capybara 34b update
* deepseek coder update
* dolphin yi update
* fix the maxtokens of islm
* lzlv 70b update
* marx3b update
* mythomax 13b update
* update neural chat 7b
* noromaid 20b update
* update openchat 7b
* openhermes7b update
* openorca 7b
* orca 13b update
* phind 34b update
* rocket 3b update
* starling 7b update
* storytelling 70b update
* tiefighter 13B
* update tiefighter tags
* tinyllama update
* wizard coder 13b
* update wizard coder 13b description
* wizard coder 34b update
* wizard coder minor fix
* xwin 70b update
* yarn 70b
* yi 34b
* zephyr beta 7b
* neuralhermes-7b update
* change path + ctxlen
* update id
* fix startling
2023-12-01 17:20:58 +07:00
