README.md

metadata

license: mit
language:
  - en
  - zh
metrics:
  - accuracy
base_model:
  - Qwen/Qwen3-32B
pipeline_tag: text-generation
library_name: transformers
tags:
  - blockchain
  - conversational
  - web3
  - qwen3
eval_results:
  - task: domain-specific evaluation
    dataset: DMindAI/DMind_Benchmark
    metric: normalized web3 score
    score: 77.44
    model: DMind-1
    model_rank: 1 / 24

---

Table of Contents

• Introduction
• 1. Model Overview
• 2. Evaluation Results
• 3. Use Cases
• 4. Quickstart
  • 4.1 Model Downloads
  • 4.2 OpenRouter API
  • 4.3 OpenRouter Web Chat
• License
• Contact

Introduction

The rapid growth of Web3 technologies—blockchain, DeFi, and smart contracts—demands specialized AI large language models (LLMs) with precise domain alignment and advanced reasoning capabilities. However, General-purpose LLMs often lack the domain-specific accuracy, nuanced reasoning, and instruction-following aligned with expert expectations.

To address these limitations, we introduce DMind-1, a domain-specialized LLM fine-tuned for the Web3 ecosystem via supervised instruction tuning and reinforcement learning from human feedback (RLHF). Built on a powerful base model, DMind-1 achieves strong improvements in task accuracy, content safety, and expert-aligned interaction, significantly surpassing general-purpose models. DMind-1 represents a robust foundation for intelligent agents in the Web3 ecosystem.

1. Model Overview

DMind-1

DMind-1 is a specialized Web3 expert model built on the Qwen3-32B base. Leveraging a state-of-the-art transformer architecture, it integrates deep domain knowledge through a novel two-stage fine-tuning pipeline, establishing its distinctive strengths in Web3-specific applications.

Key Points:

• Comprehensive Domain Expertise Data: In the first stage, DMind-1 underwent Supervised Fine-Tuning (SFT) on 13,276 expert-curated knowledge items distilled from 32.7GB of Web3 documentation, covering 8 key subdomains including DeFi, tokenomics, governance, and smart contracts. These data points were extracted and structured by a team of domain experts to ensure both depth and accuracy. To enable efficient and scalable training, we employed Low-Rank Adaptation (LoRA) during the SFT stage, allowing DMind-1 to internalize specialized Web3 knowledge while preserving the general-language capabilities of its base model.

• Reinforcement Learning from Human Feedback (RLHF) To further align the model with expert expectations in realistic interaction scenarios and accuracy, we implemented an RLHF phase composed of:

  • Reward Model Training: We trained a domain-specific reward model using preference-ranked outputs collected from human experts across diverse Web3-specific question-answer and interaction scenarios. This model learned to assess which responses best reflect factual accuracy and expert-level reasoning in the Web3 domain.
  • Policy Optimization with PPO: Building on the SFT model, we fine-tuned Qwen3-32B using Proximal Policy Optimization (PPO), guided by the trained reward model. The policy network was optimized based on feedback from simulated Web3 dialogue environments, while LoRA ensured resource-efficient parameter updates and significantly reduced compute and memory requirements. This dual-stage approach enabled efficient fine-tuning of a larger model on Web3-specific tasks while achieving high alignment with human intent.

• Domain-Aligned Reasoning and Interaction: DMind-1 exhibits advanced web3-aligned reasoning and interactive capabilities in the following fields:

  • Natural Dialogue Fluency: Coherent, context-aware conversations on complex Web3 topics, with strong multi-turn consistency.

  • Complex Instruction Following: Reliable execution of multi-step instructions and conditional logic, supporting agent-driven workflows.

  • Safe and Compliant Content Generation: Outputs are aligned with domain-specific safety, ethics, and regulatory standards.

2. Evaluation Results

We evaluate DMind-1 using the DMind Benchmark, a domain-specific evaluation suite tailored to assess large language models in the Web3 context. The benchmark spans 1,917 expert-reviewed questions across nine critical categories—including Blockchain Fundamentals, Infrastructure, Smart Contracts, DeFi, DAO, NFT, Token Economics, Meme, and Security. It combines multiple-choice and subjective open-ended tasks, simulating real-world challenges and requiring deep contextual understanding, which provides a comprehensive assessment of both factual knowledge and advanced reasoning.

Under this rigorous evaluation, DMind-1 ranked 1st among 24 leading models, outperforming both proprietary (e.g., Grok-3) and open-source (e.g., DeepSeek-R1) LLMs. Notably, our distilled variant DMind-1-mini also performed strongly, ranking 2nd overall. This demonstrates the effectiveness of our compact distillation pipeline.

3. Use Cases

• Expert-Level Question & Answering: Provides accurate, context-aware answers on blockchain, DeFi, smart contracts, and related Web3 topics.
• Compliance-Aware Support: Assists in drafting or reviewing content within regulatory and legal contexts.
• Content Generation in Domain: Produces Web3-specific blog posts, documentation, and tutorials tailored to developers and users.
• DeFi Strategy Suggestions: Generates insights and recommendations for yield farming, liquidity provision, and portfolio strategies based on user-provided data.
• Risk Management: Suggests strategies aligned with user risk profiles for more informed decision-making in volatile markets.

4. Quickstart

4.1 Model Downloads

Model	Base Model	Download
DMind-1	Qwen3-32B	Hugging Face Link
DMind-1-mini	Qwen3-14B	Hugging Face Link

4.2 OpenRouter API

You can access DMind-1 via the OpenRouter API. Simply specify the desired model in the model field of your request payload.

API Endpoint:

https://openrouter.ai/api/v1/chat/completions

Authentication:

• Obtain your API key from OpenRouter
• Include it in the Authorization header as Bearer YOUR_API_KEY

Model Identifiers:

• dmind-1 — Full-size expert model

Example Request (Python):

import requests

headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

data = {
    "model": "dmind-1",
    "messages": [
        {"role": "user", "content": "Explain DeFi in simple terms."}
    ]
}

response = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers=headers,
    json=data
)
print(response.json())

Example Request (cURL):

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dmind-1",
    "messages": [{"role": "user", "content": "What is a smart contract?"}]
  }'

Notes:

• Replace YOUR_API_KEY with your actual OpenRouter API key.
• Change the model field to dmind-1 as needed.
• Both models support the same API structure for easy integration.

4.3 OpenRouter Web Chat

You can try DMind-1 instantly using the OpenRouter Web Chat.

• Select your desired model from the dropdown menu (DMind-1).
• Enter your prompt and interact with the model in real time.

License

• The code repository and model weights for DMind-1 is released under the MIT License.
• Commercial use, modification, and derivative works (including distillation and fine-tuning) are permitted.
• Base Models:
  • DMind-1 is derived from Qwen3-32B, originally licensed under the Qwen License.
  • Please ensure compliance with the original base model licenses when using or distributing derivatives.

Contact

For questions or support, please contact [email protected]