modelscope /modelscope
ModelScope: bring the notion of Model-as-a-Service to life.
★ 9,218⑂ 977👁 79⑃ 856● 972▤ 80
+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 - OffliTop issues
#1658ModelScope于llama.cpp集成无法使用14 comments · 2026-03-27#1809MCP 广场:外部 OAuth Streamable HTTP 服务配置后仍不可部署、未提供工具信息4 comments · 2026-10-05#1842关于 model scope 的API 推理接口是否已支持了音频推理?3 comments · 2026-11-04#1828Mirror of `kernels-community/*` stopped syncing, and has no kernel version branches3 comments · 2026-10-23#18262560x1600分辨率电脑edge打开设计师(AIGC)模板样式个人主页,页面顶端抽动会让CPU/GPU占用率飙升3 comments · 2026-10-22#1822ModelScope绑定的阿里云PAI默认工作空间误删除问题2 comments · 2026-10-14#1849创空间免费 16G CPU(platform/2v-cpu-16g-mem)重新部署后一直「部署中」,ossfs 挂载后应用进程从未启动1 comments · 2026-11-10#1827创空间仓库不小心推了几个无用分支,发现无权限删除1 comments · 2026-10-22
Discussions
#1605You have CSAM on your site1 comments · 2026-02-03#1536如何创建或者下载mcp bundle0 comments · 2025-11-01#1523魔搭的网站出什么Bug了,一点击“模型文件”按钮,就Error页2 comments · 2025-10-11#1387页面有bug点击执行跨域了1 comments · 2025-06-28#1322运行qwen2.5-vl-3b-instrcut-awq时,报错:ImportError: cannot import name 'shard_checkpoint' from 'transformers.modeling_utils' (C:\Users\long\PycharmProjects\qwenvl\.venv\lib\site-packages\transformers\modeling_utils.py)0 comments · 2025-04-25#1310change iotdb-mcp-server, use apache version1 comments · 2025-04-15#1309Add New MCP Server in MCP Square1 comments · 2025-04-15#1295为什么 Qwen2.5-Omni-7B 官方教程都报错 Cannot import available module of Qwen2_5OmniModel in modelscope ?1 comments · 2025-04-02
Latest release
v1.40.3 v1.40.3 2026-11-09Enhance - 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