modelscope /modelscope

ModelScope: bring the notion of Model-as-a-Service to life.

★ 9,218⑂ 977👁 79⑃ 856● 972▤ 80
PythonApache-2.0Created 2022-07-25www.modelscope.cn/
More from this author
Download: v1.40.3v1.40.3 ↓1.40.32026-11-09
+4
Daily
9,218
stars
977
forks
79
watchers
856
prs
972
issues
80
releases

README

Discord






    
        English |
        中文 |
        日本語
    





 Introduction

ModelScope is built upon the notion of “Model-as-a-Service” (MaaS). It seeks to bring together most advanced machine learning models from the AI community, and streamlines the process of leveraging AI models in real-world applications. The core ModelScope library open-sourced in this repository provides the interfaces and implementations that allow developers to perform  model inference, training and evaluation.


In particular, with rich layers of API-abstraction, the ModelScope library offers unified experience to explore state-of-the-art models spanning across domains such as CV, NLP, Speech, Multi-Modality, and Scientific-computation. Model contributors of different areas can integrate models into the ModelScope ecosystem through the layered-APIs, allowing easy and unified access to their models. Once integrated, model inference, fine-tuning, and evaluations can be done with only a few lines of codes. In the meantime, flexibilities are also provided so that different components in the model applications can be customized wherever necessary.

Apart from harboring implementations of a wide range of different models, ModelScope library also enables the necessary interactions with ModelScope backend services, particularly with the Model-Hub and Dataset-Hub. Such interactions facilitate management of  various entities (models and datasets) to be performed seamlessly under-the-hood, including entity lookup, version control, cache management, and many others.

 Models and Online Accessibility

Hundreds of models are made publicly available on ModelScope  (700+ and counting), covering the latest development in areas such as NLP, CV, Audio, Multi-modality, and AI for Science, etc. Many of these models represent the SOTA in their specific fields, and made their open-sourced debut on ModelScope. Users can visit ModelScope(modelscope.cn) and experience first-hand how these models perform via online experience, with just a few clicks. Immediate developer-experience is also possible through the ModelScope Notebook, which is backed by ready-to-use CPU/GPU development environment in the cloud - only one click away on ModelScope.



    
    
    


Some representative examples include:

LLM:

 Yi-1.5-34B-Chat

 Qwen1.5-110B-Chat

 DeepSeek-V2-Chat

 Ziya2-13B-Chat

 Meta-Llama-3-8B-Instruct

 Phi-3-mini-128k-instruct


Multi-Modal:

 Qwen-VL-Chat

 Yi-VL-6B

 InternVL-Chat-V1-5

 deepseek-vl-7b-chat

 OpenSoraPlan

 OpenSora

 I2VGen-XL

CV:

 DamoFD Face Detection Key Point Model - 0.5G

 BSHM Portrait Matting

 DCT-Net Portrait Cartoonization - 3D

 DCT-Net Portrait Cartoonization Model - 3D

 DuGuang - Text Recognition - Line Recognition Model - Chinese and English - General Domain

 DuGuang - Text Recognition - Line Recognition Model - Chinese and English - General Domain

 LaMa Image Inpainting


Audio:

 Paraformer Speech Recognition - Chinese - General - 16k - Offli

Top issues

Discussions

Latest release

v1.40.3 v1.40.3 2026-11-09
Enhance
- Requires modelscope-hub=0.7.0.
- New modelscope.utils.file_utils.get_hub_cache_root(); modelscope.hub.cache_manager re-exports get_cache_root and resolve_cached_snapshot. MS_CACHE_HOME is normalised to an absolute path when bridged into the hub config.

Fix
- model_file_download(..., local_files_only=True) no longer calls the API to resolve the default revision, so offline downloads from cache work without network access or credentials.
- ms clear-cache lists every resolved target before deleting and delegates to modelscope-hub's scoped cache APIs; cache deletion via FileSystem

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON