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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wubingheng/Doge-20M-Medical-SFT", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("wubingheng/Doge-20M-Medical-SFT", trust_remote_code=True)
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wubingheng/Doge-20M-Medical-SFT"
# 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-Medical-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

Model Card for Doge-20M-Medical-SFT

This model is a fine-tuned version of wubingheng/Doge-20M-Chinese. It has been trained using TRL.

Quick start

from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig, TextStreamer
tokenizer = AutoTokenizer.from_pretrained("wubingheng/Doge-20M-Medical-SFT")
model = AutoModelForCausalLM.from_pretrained("wubingheng/Doge-20M-Medical-SFT", trust_remote_code=True)
generation_config = GenerationConfig(
    max_new_tokens=40,
    min_new_tokens=1,
    num_beams=1,
    eos_token_id=[tokenizer.eos_token_id],
    stop_strings=[tokenizer.eos_token],
    early_stopping=False,
    use_cache=True,
    do_sample=True,
    temperature=0.95,
    repetition_penalty=1.0,
)
steamer = TextStreamer(tokenizer=tokenizer, skip_prompt=True)

system_prompt = """
    你是一个医学助手，能够回答用户提出的医学问题。请根据用户的问题，给出准确的医学建议和解答。

""".strip()

prompt = "肝癌术后饮食注意事项有哪些" 
conversation = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": prompt},
]
inputs = tokenizer.apply_chat_template(
    conversation=conversation,
    tokenize=True,
    return_tensors="pt",
)
print(prompt)

output = model.generate(
    inputs, 
    tokenizer=tokenizer,
    generation_config=generation_config, 
    streamer=steamer
)

Training procedure

This model was trained with SFT.

Framework versions

TRL: 0.15.2
Transformers: 4.51.2
Pytorch: 2.6.0+cu126
Datasets: 3.2.0
Tokenizers: 0.21.0

Citations

@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}
}

Downloads last month: 4

Safetensors

Model size

13.1M params

Tensor type

BF16

Model tree for wubingheng/Doge-20M-Medical-SFT

Base model

wubingheng/Doge-20M-Chinese

Finetuned

(1)

this model

wubingheng
/

Doge-20M-Medical-SFT