You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
I reviewed the Discussions, and have a new and useful enhancement to share.
Feature Description
ModelScope is the one of the leading open-model communities, and has recently incorporated native support for llamafile through it command line tools.
Simply install ModelScope with pip install modelscope -U, and you will have access to a wealth of llamafile models on ModelScope. Get it up and running with ModelScope command modelscope llamafile --model {model_id} , for example: modelscope llamafile --model Qwen-Llamafile/Qwen2.5-3B-Instruct-llamafile.
There are also a few other running options such as to specify quantiazation level: modelscope llamafile --model Qwen-Llamafile/Qwen2.5-3B-Instruct-llamafile --accuracy Q2_K
More details can be found in documentation here and here (a bit of google translation needed since the doc is in Chinease).
Currently there are 350+ llamafile repos on ModelScope, covering almost all major LLMs. It is definitely the largest collection out there. All of which you can access directly via link.
Prerequisites
Feature Description
ModelScope is the one of the leading open-model communities, and has recently incorporated native support for llamafile through it command line tools.
Simply install ModelScope with
pip install modelscope -U
, and you will have access to a wealth of llamafile models on ModelScope. Get it up and running with ModelScope commandmodelscope llamafile --model {model_id}
, for example:modelscope llamafile --model Qwen-Llamafile/Qwen2.5-3B-Instruct-llamafile
.There are also a few other running options such as to specify quantiazation level:
modelscope llamafile --model Qwen-Llamafile/Qwen2.5-3B-Instruct-llamafile --accuracy Q2_K
More details can be found in documentation here and here (a bit of google translation needed since the doc is in Chinease).
Currently there are 350+ llamafile repos on ModelScope, covering almost all major LLMs. It is definitely the largest collection out there. All of which you can access directly via link.
ModelScope is also open sourced at https://github.com/modelscope/modelscope
Motivation
We are glad to share this new feature with the llamafile comunities, and we welcome any new request or contribution of new llamafiles to ModelScope!
Cheers.
Possible Implementation
No response
The text was updated successfully, but these errors were encountered: