Instructions to use DMindAI/DMind-3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DMindAI/DMind-3 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="DMindAI/DMind-3")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("DMindAI/DMind-3")
model = AutoModelForImageTextToText.from_pretrained("DMindAI/DMind-3")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DMindAI/DMind-3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DMindAI/DMind-3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DMindAI/DMind-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DMindAI/DMind-3

SGLang

How to use DMindAI/DMind-3 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "DMindAI/DMind-3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DMindAI/DMind-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "DMindAI/DMind-3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DMindAI/DMind-3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DMindAI/DMind-3 with Docker Model Runner:
```
docker model run hf.co/DMindAI/DMind-3
```

yuzhe commited on Jan 27

Commit

aa774d8

verified ·

1 Parent(s): 003f531

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -23

README.md CHANGED Viewed

@@ -142,30 +142,8 @@ Evaluated on three key benchmarks: **DMind Benchmark** (Web3 Native Logic), **Fi
 The evaluation compares DMind-3 (21B) against top-tier frontier models (GPT-5.1, Claude Sonnet 4.5) and other efficient models. Despite its optimized size, the Max model demonstrates exceptional efficiency, particularly in specialized domain tasks where it outperforms significantly larger generalist models.
-### 8. 🚀 API Access & Quick Start
-Access to DMind-3 is provided via a secure, high-throughput API. Enterprise clients can also opt for private VPC deployment.
-**Example API Call (Python):**
-```python
-import dmind_api
-dmind_api.api_key = "YOUR_API_KEY"
-response = dmind_api.Completion.create(
-    model="dmind-3",
-    prompt="Model the potential contagion effects of a 50% drop in stETH collateral value across the top 5 lending protocols on Ethereum and Base. Provide a probabilistic assessment of liquidation cascades.",
-    max_tokens=2048,
-    temperature=0.2, # Low temperature for analytical tasks
-    top_p=1.0
-)
-print(response.choices[0].text)
-```
-[→ View Full API Documentation](https://docs.dmind.ai/max/api)
-### 9. ⚖️ Limitations & Disclaimer
 - **Not a Financial Advisor (NFA)**: DMind-3 is a powerful analytical tool for generating insights and modeling risks. It is not a registered financial advisor. All outputs should be independently verified and are not a solicitation to trade.
 - **Probabilistic Nature**: All forecasts are probabilistic and based on the data available up to the knowledge cutoff. The model cannot predict black swan events and is subject to the inherent unpredictability of markets.

 The evaluation compares DMind-3 (21B) against top-tier frontier models (GPT-5.1, Claude Sonnet 4.5) and other efficient models. Despite its optimized size, the Max model demonstrates exceptional efficiency, particularly in specialized domain tasks where it outperforms significantly larger generalist models.
+### 8. ⚖️ Limitations & Disclaimer
 - **Not a Financial Advisor (NFA)**: DMind-3 is a powerful analytical tool for generating insights and modeling risks. It is not a registered financial advisor. All outputs should be independently verified and are not a solicitation to trade.
 - **Probabilistic Nature**: All forecasts are probabilistic and based on the data available up to the knowledge cutoff. The model cannot predict black swan events and is subject to the inherent unpredictability of markets.