OpenCSG(开放传神) 打造 Hybrid Huggingface plus 开源社区开放传神 OpenCSG 传神社区官网

Empowering Everyone with Large Language Models

To Build Hybrid HuggingFace+

Empowering Everyone with Large Language Models

To Build Hybrid HuggingFace+

Empowering Everyone with Large Language Models

To Build Hybrid HuggingFace+

Empowering Everyone with Large Language Models

To Build Hybrid HuggingFace+

Empowering Everyone with Large Language Models

To Build Hybrid HuggingFace+

Empowering Everyone with Large Language Models

To Build Hybrid HuggingFace+

Open-source platform for large models

Supports full-cycle development for large model

Showcases the latest research and papers

Document center

Product FAQs and Overview

Trending this week

Explore the Latest Models, Datasets and Space

Models

Datasets

Spaces

Num：0

Model hub is a place where models are hosted for storage, management, discovery and sharing. You can create your own model repository, upload, download and manage model files. It makes exploring and using models as easy as possible.

OpenCSG/csg-wukong-1B

csg-wukong-1B是OpenCSG算法团队打造的人人都能负担得起的自研预训练通用语言模型，具有1B的参数量，在模型不量化的情况下仅需3G内存即可部署在PC端、手机端以及其他IOT设备上。

Last Updated：2024-04-21

Last Updated：2025-03-05

deepseek-ai/DeepSeek-R1

Last Updated：2025-01-20

deepseek-ai/DeepSeek-V3

Last Updated：2025-01-06

OpenCSG/OpenCSG-R1-Qwen2.5-Math-3B-V1

Last Updated：2025-02-16

AIWizards/Wan2.1-T2V-14B

Last Updated：2025-02-25

Cloud Computing Resources

Offering a variety of computing services, tailored leasing plans are available.

30+

Supplier

8000P+

Resource

1+N

Type

40%+

Favorable

01

Application Prototype Hosting

Quickly Build Prototype Applications in Space, Enhance Development Efficiency

Prototype display

Efficient

Flexible

02

02

One-click Inference Service

Simplifying the Deploy Process Without Complex Configurations

03

03

One-click Fine-Tuning

Launch Model Fine-Tuning on Specific Datasets with One-click

OpenCSG Product Roadmap

We are dedicated to building a community for LLM, uniting AI enterprises to collaboratively deliver products and solutions for customers.

"

PROMPT

CODE

BUILD

TEST

RELRASE

DEPLOY

OPERATE

RETRAIN

PROMPT

CODE

BUILD

TEST

RELRASE

DEPLOY

OPERATE

RETRAIN

Agentic

Ops

Step2. StarShip

Generate, review, and testing codes

Step1. StarShip

Enter prompts in IDE

Custom workflow

Automate tasks by user intent

EndPoint, Serverless API

Deploy AI apps and Agents in production

Step3. StarShip

Deploy Agents and AI apps

Step4. StarShip

Test AI apps in virtual environments

Step5. StarShip

Deploy Agents and AI apps

Finetune, Evaluation

Iterate and upgrade AI apps and Agents

Continuous data collection

All-in-one data processing platform

Your browser automation assistant

Automated Workflows

Intelligent agent collaboration platform

Automated Workflow

High Scalability

Intelligent Collaboration

Open-source, trusted LM and Agents management platform

Efficient Resource Management

Data Synchronization

Data Compliance

Robust open-source ecosystem with comprehensive services and frameworks.

Welcome your use, feedback, and participation in co-development. Don't forget to follow us and give us a Star

Assets Management

Resource Scheduling

One-click Fine-tuning

One-click Inference

CSGHub is an open source, trustworthy large model asset management platform that can assist users in governing the assets involved in the lifecycle of LLM and LLM applications (datasets, model files, codes, etc).

llm-inference is a platform for publishing and managing llm inference, providing a wide range of out-of-the-box features for model deployment, such as UI, RESTful API, auto-scaling, computing resource management, monitoring, and more.

The framework of training large language models，support lora, full parameters fine tune etc, define yaml to start training/fine tune of your defined models, data and methods.

CSGHub is an open source, trustworthy large model asset management platform that can assist users in governing the assets involved in the lifecycle of LLM and LLM applications (datasets, model files, codes, etc).

llm-inference is a platform for publishing and managing llm inference, providing a wide range of out-of-the-box features for model deployment, such as UI, RESTful API, auto-scaling, computing resource management, monitoring, and more.

The framework of training large language models，support lora, full parameters fine tune etc, define yaml to start training/fine tune of your defined models, data and methods.

StarCloud is an open source web interface to LLM jobs. the scheduler engine is using Slurm as default engine It performs large model jobs scheduling based on GPU resources.

The CSGHub SDK is a powerful Python client specifically designed to interact seamlessly with the CSGHub server. This toolkit is engineered to provide Python developers with an efficient and straightforward method to operate and manage remote CSGHub instances. Whether you're looking to automate tasks, manage data, or integrate CSGHub functionalities into your Python applications, the CSGHub SDK offers a comprehensive set of features to accomplish your goals with ease.

CSGHub Server is the backend server for CSGHub which helps user to manage datasets, model files, codes and more.

StarCloud is an open source web interface to LLM jobs. the scheduler engine is using Slurm as default engine It performs large model jobs scheduling based on GPU resources.

The CSGHub SDK is a powerful Python client specifically designed to interact seamlessly with the CSGHub server. This toolkit is engineered to provide Python developers with an efficient and straightforward method to operate and manage remote CSGHub instances. Whether you're looking to automate tasks, manage data, or integrate CSGHub functionalities into your Python applications, the CSGHub SDK offers a comprehensive set of features to accomplish your goals with ease.

CSGHub Server is the backend server for CSGHub which helps user to manage datasets, model files, codes and more.

CSG-VL is a family of small but strong multimodal models. It offers multiple plug-and-play vision encoders, like EVA-CLIP, SigLIP and language backbones, including Wukong-1B, Llama-3-8B, Phi-1.5, StableLM-2, Qwen1.5 and Phi-2.

A survey of small language models

SWE-Bench Experiments

This repository contains the predictions, execution logs, trajectories, and results for model inference + evaluation runs on the SWE-bench task.

CSG-VL is a family of small but strong multimodal models. It offers multiple plug-and-play vision encoders, like EVA-CLIP, SigLIP and language backbones, including Wukong-1B, Llama-3-8B, Phi-1.5, StableLM-2, Qwen1.5 and Phi-2.

A survey of small language models

SWE-Bench Experiments

This repository contains the predictions, execution logs, trajectories, and results for model inference + evaluation runs on the SWE-bench task.

CSGHub is an open source, trustworthy large model asset management platform that can assist users in governing the assets involved in the lifecycle of LLM and LLM applications (datasets, model files, codes, etc).

llm-inference is a platform for publishing and managing llm inference, providing a wide range of out-of-the-box features for model deployment, such as UI, RESTful API, auto-scaling, computing resource management, monitoring, and more.

The framework of training large language models，support lora, full parameters fine tune etc, define yaml to start training/fine tune of your defined models, data and methods.

StarCloud is an open source web interface to LLM jobs. the scheduler engine is using Slurm as default engine It performs large model jobs scheduling based on GPU resources.

The CSGHub SDK is a powerful Python client specifically designed to interact seamlessly with the CSGHub server. This toolkit is engineered to provide Python developers with an efficient and straightforward method to operate and manage remote CSGHub instances. Whether you're looking to automate tasks, manage data, or integrate CSGHub functionalities into your Python applications, the CSGHub SDK offers a comprehensive set of features to accomplish your goals with ease.

CSGHub is an open source, trustworthy large model asset management platform that can assist users in governing the assets involved in the lifecycle of LLM and LLM applications (datasets, model files, codes, etc).

llm-inference is a platform for publishing and managing llm inference, providing a wide range of out-of-the-box features for model deployment, such as UI, RESTful API, auto-scaling, computing resource management, monitoring, and more.

The framework of training large language models，support lora, full parameters fine tune etc, define yaml to start training/fine tune of your defined models, data and methods.

StarCloud is an open source web interface to LLM jobs. the scheduler engine is using Slurm as default engine It performs large model jobs scheduling based on GPU resources.

The CSGHub SDK is a powerful Python client specifically designed to interact seamlessly with the CSGHub server. This toolkit is engineered to provide Python developers with an efficient and straightforward method to operate and manage remote CSGHub instances. Whether you're looking to automate tasks, manage data, or integrate CSGHub functionalities into your Python applications, the CSGHub SDK offers a comprehensive set of features to accomplish your goals with ease.

CSGHub Server is the backend server for CSGHub which helps user to manage datasets, model files, codes and more.

CSG-VL is a family of small but strong multimodal models. It offers multiple plug-and-play vision encoders, like EVA-CLIP, SigLIP and language backbones, including Wukong-1B, Llama-3-8B, Phi-1.5, StableLM-2, Qwen1.5 and Phi-2.

A survey of small language models

SWE-Bench Experiments

This repository contains the predictions, execution logs, trajectories, and results for model inference + evaluation runs on the SWE-bench task.

CSGHub Server is the backend server for CSGHub which helps user to manage datasets, model files, codes and more.

CSG-VL is a family of small but strong multimodal models. It offers multiple plug-and-play vision encoders, like EVA-CLIP, SigLIP and language backbones, including Wukong-1B, Llama-3-8B, Phi-1.5, StableLM-2, Qwen1.5 and Phi-2.

A survey of small language models

SWE-Bench Experiments

This repository contains the predictions, execution logs, trajectories, and results for model inference + evaluation runs on the SWE-bench task.

CSGHub is an open source, trustworthy large model asset management platform that can assist users in governing the assets involved in the lifecycle of LLM and LLM applications (datasets, model files, codes, etc).

llm-inference is a platform for publishing and managing llm inference, providing a wide range of out-of-the-box features for model deployment, such as UI, RESTful API, auto-scaling, computing resource management, monitoring, and more.

The framework of training large language models，support lora, full parameters fine tune etc, define yaml to start training/fine tune of your defined models, data and methods.

StarCloud is an open source web interface to LLM jobs. the scheduler engine is using Slurm as default engine It performs large model jobs scheduling based on GPU resources.

The CSGHub SDK is a powerful Python client specifically designed to interact seamlessly with the CSGHub server. This toolkit is engineered to provide Python developers with an efficient and straightforward method to operate and manage remote CSGHub instances. Whether you're looking to automate tasks, manage data, or integrate CSGHub functionalities into your Python applications, the CSGHub SDK offers a comprehensive set of features to accomplish your goals with ease.

CSGHub Server is the backend server for CSGHub which helps user to manage datasets, model files, codes and more.

Our Customers

Connect and build a solution ecosystem together with partners to establish a new ecosystem of co-creation, win-win and sharing.

Become a partner

Become a partner

Boosting Business with Open-Source Large Models

OpenCSG helps you find the suitable and cost-effective open-source large models.

Models

Datasets

Spaces

Models

Datasets

Spaces

About CSGHub Models

Model hub is a place where models are hosted for storage, management, discovery and sharing. You can create your own model repository, upload, download and manage model files. It makes exploring and using models as easy as possible.

加载失败

About us

Contact us

Corporate:
partner@opencsg.com

Careers:
hr@opencsg.com

Press Relations:
pr@opencsg.com

Investor Relations:
ir@opencsg.com

Follow OpenCSG

Follow the OpenCSG official account to stay updated with real-time information.

©Copyright 2025 OpenCSG.com

User Agreement & Privacy Policy complaint & suggestions

Beijing public network security 11011202004415

Beijing ICPB 2023006263-1

｜

中文

EN

User Agreement & Privacy Policy

©Copyright 2025 OpenCSG.com

Beijing public network security 11011202004415

Beijing ICPB 2023006263-1