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

003f531

verified ·

1 Parent(s): 01ed042

Update README.md

Browse files

Files changed (1) hide show

README.md +29 -1

README.md CHANGED Viewed

@@ -1,3 +1,27 @@
 # 🔮 DMind-3: The Age of Foresight
 *From local logic to global foresight. In a world of isolated systems, the one who sees the whole board wins.*
@@ -38,6 +62,8 @@ This final piece of the trilogy moves beyond the tactical and into the strategic
 DMind-3 introduces **Hierarchical Predictive Synthesis (HPS)**. While C³-SFT (used in `mini`) teaches the model to correct its own reasoning, HPS teaches it to synthesize multiple, conflicting, time-variant data streams into a coherent probabilistic forecast. It operates on a nested hierarchy of abstraction, from raw on-chain events to complex macroeconomic indicators.
 **(Figure 1: The HPS training paradigm, showing multi-level data fusion and probabilistic future state generation)**
 **Mathematical Formalization**
@@ -86,6 +112,8 @@ DMind-3 is designed to power the next generation of DeFi analytics, risk managem
 The DMind-3 series is a vertically integrated stack designed for sovereign intelligence.
 **(Figure 2: The full DMind-3 Cognitive Architecture, from on-device reflexes to cloud-native foresight)**
 - **The Oracle (DMind-3)**: Runs in the cloud. Provides macro-strategic foresight, systemic risk analysis, and orchestrates the agent fleet.
@@ -143,4 +171,4 @@ print(response.choices[0].text)
 - **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.
 - **Knowledge Cutoff**: The core model has a knowledge cutoff of June 2025. While it can process real-time data provided via the API, its foundational understanding is based on its training corpus.
----

+---
+language:
+- en
+- zh
+license: apache-2.0
+library_name: transformers
+tags:
+- web3
+- finance
+- defi
+- chain-of-thought
+- sft
+- security-audit
+- on-device-ai
+metrics:
+- accuracy
+- ponzi-detection-rate
+- code-security-score
+pipeline_tag: text-generation
+inference: false
+base_model:
+- openai/gpt-oss-20b
+---
 # 🔮 DMind-3: The Age of Foresight
 *From local logic to global foresight. In a world of isolated systems, the one who sees the whole board wins.*
 DMind-3 introduces **Hierarchical Predictive Synthesis (HPS)**. While C³-SFT (used in `mini`) teaches the model to correct its own reasoning, HPS teaches it to synthesize multiple, conflicting, time-variant data streams into a coherent probabilistic forecast. It operates on a nested hierarchy of abstraction, from raw on-chain events to complex macroeconomic indicators.
+![Figure 1](./Figures/Figure1.png)
 **(Figure 1: The HPS training paradigm, showing multi-level data fusion and probabilistic future state generation)**
 **Mathematical Formalization**
 The DMind-3 series is a vertically integrated stack designed for sovereign intelligence.
+![Figure 2](./Figures/Figure2.png)
 **(Figure 2: The full DMind-3 Cognitive Architecture, from on-device reflexes to cloud-native foresight)**
 - **The Oracle (DMind-3)**: Runs in the cloud. Provides macro-strategic foresight, systemic risk analysis, and orchestrates the agent fleet.
 - **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.
 - **Knowledge Cutoff**: The core model has a knowledge cutoff of June 2025. While it can process real-time data provided via the API, its foundational understanding is based on its training corpus.
+---