Instructions to use wubingheng/Doge-20M-Chinese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wubingheng/Doge-20M-Chinese with Transformers:

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

pipe = pipeline("text-generation", model="wubingheng/Doge-20M-Chinese", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wubingheng/Doge-20M-Chinese", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("wubingheng/Doge-20M-Chinese", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wubingheng/Doge-20M-Chinese with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wubingheng/Doge-20M-Chinese"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wubingheng/Doge-20M-Chinese",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wubingheng/Doge-20M-Chinese

SGLang

How to use wubingheng/Doge-20M-Chinese 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 "wubingheng/Doge-20M-Chinese" \
    --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": "wubingheng/Doge-20M-Chinese",
		"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 "wubingheng/Doge-20M-Chinese" \
        --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": "wubingheng/Doge-20M-Chinese",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wubingheng/Doge-20M-Chinese with Docker Model Runner:
```
docker model run hf.co/wubingheng/Doge-20M-Chinese
```

Doge-20M-Chinese / README.md

wubingheng

Update README.md

da08ea2 verified over 1 year ago

preview code

Raw History Blame

3.13 kB

metadata

library_name: transformers
license: apache-2.0
datasets:
  - HuggingFaceTB/smollm-corpus
language:
  - en
pipeline_tag: text-generation
tags:
  - pt
  - doge

Doge 20M

Doge uses Dynamic Mask Attention as sequence transformation and can use Multi-Layer Perceptron or Cross Domain Mixture of Experts as state transformation. Dynamic Mask Attention allows the Transformer to use self-attention during training and state space during inference, and Cross Domain Mixture of Experts can directly inherit the weights of Multi-Layer Perceptron for further training. This model is trained by SmallDoge community, for detailed algorithm and model architecture, paper coming soon, all training details and code are available in the small-doge repository.

Uses

>>> from transformers import AutoTokenizer, AutoModelForCausalLM

>>> tokenizer = AutoTokenizer.from_pretrained("wubingheng/Doge-20M-Chinese")
>>> model = AutoModelForCausalLM.from_pretrained("wubingheng/Doge-20M-Chinese", trust_remote_code=True)
>>> inputs = tokenizer("Hey how are you doing?", return_tensors="pt")

>>> out = model.generate(**inputs, max_new_tokens=100)
>>> print(tokenizer.batch_decode(out))

Model Details

Environment:

Image: nvcr.io/nvidia/pytorch:24.12-py3
Hardware: 1x NVIDIA RTX 4090
Software: Transformers

Citation

@misc{smalldoges,
  title={SmallDoges: A Family of Dynamic UltraFast Small Language Models}, 
  author={Jingze, Shi and Yifan, Wu and Bingheng, Wu and Yuyu, Luo},
  year={2025},
  month={March},
  url={https://github.com/SmallDoges/small-doge}
}