Text Generation
Transformers
Safetensors
English
Chinese
function-calling
tool-use
crypto
blockchain
solana
ethereum
on-device
privacy
edge-ai
mobile
wallet
standard-protocol
Instructions to use DMindAI/DMind-3-nano with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DMindAI/DMind-3-nano with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DMindAI/DMind-3-nano")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("DMindAI/DMind-3-nano", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use DMindAI/DMind-3-nano with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DMindAI/DMind-3-nano" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DMindAI/DMind-3-nano", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/DMindAI/DMind-3-nano
- SGLang
How to use DMindAI/DMind-3-nano 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-nano" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DMindAI/DMind-3-nano", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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-nano" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DMindAI/DMind-3-nano", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use DMindAI/DMind-3-nano with Docker Model Runner:
docker model run hf.co/DMindAI/DMind-3-nano
Commit History
-
Replace model directory files from local upload
Verified signaturee02dc5f
-
Remove mistakenly uploaded root-level model files
Verified signaturef839a23 -
Add files using upload-large-folder tool
Verified signature96cec3e -
Add files using upload-large-folder tool
Verified signature0e7b1db
-
Update README with official FunctionGemma calling format
Verified signature- Use AutoProcessor instead of AutoTokenizer - Add tools parameter to apply_chat_template - Include complete tool schemas in example - Match official Google Gemma documentation pattern0532c27 -
Add usage principles for developer prompt
- Add usage principles section with clear rules - Emphasize placing developer prompt only once at session start - Clarify not to include in user/assistant messages - Provide correct usage pattern example 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>d5f5aec -
Add .gitignore for repository
- Ignore macOS .DS_Store files - Ignore Python cache and build artifacts - Ignore virtual environment directories - Ignore IDE configuration files 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>944a301 -
Update model configuration and tokenizer files
- Updated model config, generation config, and tokenizer settings - Removed outdated files (added_tokens.json, special_tokens_map.json, tokenizer.model, training_args.bin) - Updated model weights (model.safetensors) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>2ad36a6 -
fix(prompt): restore missing system prompts to enhance model capabilities (#1)
b772715 -
Update README with Developer Prompt section
Verified signature25f48de -
Update model/tokenizer_config.json
Verified signature3f37d70 -
Update model/tokenizer.json
Verified signatured5dbf13 -
Update model/model.safetensors
Verified signature75f4c7d -
Update model/generation_config.json
Verified signatured6e2322 -
Update model/config.json
Verified signaturec545cc8
-
Update README.md
Verified signature00622f3
-
Update README.md
Verified signaturee047ad4
-
Update README.md
Verified signature645b051 -
Update README.md
Verified signature17d4b90 -
Upload model_comparison_chart.png
Verified signature28a25de -
Upload 10 files
Verified signature4e04a8b -
Update README.md
Verified signature8f26771 -
Upload 13 files
Verified signature6f09d40
-
Update README.md
Verified signature7a71438 -
initial commit
Verified signaturee19d675