Yuan-2.0

Visit Tool

Yuan-2.0 is an open-source large language model that supports code generation, numerical calculations, and enhanced output safety. It offers various model sizes, including 2B, 51B, and 102B parameters, with pre-training, fine-tuning, and inference scripts available.

Claim this tool

2Views

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is Yuan-2.0?

Yuan-2.0 is a new generation foundational large language model released by Inspur Information. It provides open-source access to three model sizes: Yuan2.0-102B, Yuan2.0-51B, and Yuan2.0-2B. The project includes relevant scripts for pre-training, fine-tuning, and inference services, enabling developers to further develop and customize the models. Built upon Yuan-1.0, Yuan-2.0 leverages more diverse and high-quality pre-training data and instruction fine-tuning datasets, resulting in enhanced understanding capabilities across semantics, mathematics, reasoning, code, and knowledge. The model supports commercial use under the Apache 2.0 license, with specific versions offering improved code generation in Java, C++, and Go, API tool integration for numerical calculations, and strengthened safety and value alignment.

Best used for

Ideal for developers and AI researchers who need to build and deploy custom large language models, enhance code generation capabilities, and integrate advanced numerical calculation features into their applications. Especially valuable for those looking for open-source models with strong performance in mathematics, reasoning, and code tasks.

Common actions

generate code

perform calculations

fine-tune models

deploy LLMs

conduct AI research

open-sourcelow-code/no-codecollaborationautomated workflowdeepfakeface swappinggithub copilotworkflows"AI Agents"

Capabilities

Key features

Multiple model sizes
Code generation
Numerical calculations
Enhanced output safety
Instruction fine-tuning
Pre-training scripts
Inference services

Target Audience

developer

Integrations

hugging-facefastchatllama-factoryreplicate

Pricing & Plans

Open Source

Free

FAQs

What are the available model sizes for Yuan-2.0?

Yuan-2.0 offers three main model sizes: Yuan2.0-102B, Yuan2.0-51B, and Yuan2.0-2B. These models vary in parameter count, providing flexibility for different computational resources and application requirements.

Does Yuan-2.0 support commercial use?

Yes, Yuan-2.0 models are available for commercial use without requiring explicit authorization. The use of the source code is governed by the Apache 2.0 open-source license, and users are advised to adhere to the Yuan 2.0 Model License Agreement.

What programming languages can Yuan-2.0 generate code in?

The latest Yuan2-2B-Mars-hf model specifically enhances code generation capabilities for Java, C++, and Go programming languages. This makes it suitable for developers working on projects requiring code in these specific environments.

Can Yuan-2.0 be fine-tuned for specific tasks?

Yes, Yuan-2.0 provides scripts and support for fine-tuning. It can be fine-tuned using frameworks like Llama-factory for instruction fine-tuning and FastChat for multi-turn dialogue fine-tuning, allowing customization for various applications.

What are the minimum GPU memory requirements for Yuan-2.0 inference?

For inference, the Yuan-2.0 models require varying GPU memory. The 2B model needs at least 6GB, the 51B model requires 4x80GB, and the 102B model needs 8x80GB of GPU memory.

Trending

Subcategories trending in Coding & Development

Code Assistants DevOps & Infrastructure No-Code / Low-Code Testing & QA Backend & APIs Prompt Engineering

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce