Instructions to use d-s-b/Router with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use d-s-b/Router with Transformers:

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

pipe = pipeline("text-generation", model="d-s-b/Router")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("d-s-b/Router")
model = AutoModelForCausalLM.from_pretrained("d-s-b/Router")
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 d-s-b/Router with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/d-s-b/Router

SGLang

How to use d-s-b/Router 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 "d-s-b/Router" \
    --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": "d-s-b/Router",
		"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 "d-s-b/Router" \
        --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": "d-s-b/Router",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use d-s-b/Router with Docker Model Runner:
```
docker model run hf.co/d-s-b/Router
```

Model Card for Router

This model is fine-tuned to serve as a router for reasoning tasks, classifying input queries into one of three categories:

no_reasoning – Direct factual lookup or simple recall (e.g., "What is the capital of France?")

low_reasoning – Requires light reasoning such as simple arithmetic, comparisons, or single logical steps (e.g., "If John has 5 apples and eats 2, how many are left?")

high_reasoning – Requires multi-step reasoning, deep logical chains, or complex problem-solving (e.g., "Prove that the sum of two even numbers is always even").

Quick start

from transformers import pipeline

pipe = pipeline("text-generation", model="d-s-b/Router")
messages = [
    {"role": "user", "content": "what is capital of india"}
]
pipe(messages)

Training Details

Method: Supervised fine-tuning with SFTTrainer

Objective: Multi-class classification with labels (no_reasoning, low_reasoning, high_reasoning)

Dataset: Custom dataset of queries annotated with reasoning levels.

Limitations & Bias

May misclassify borderline queries (e.g., between low_reasoning and high_reasoning).

Performance depends on the diversity of training data.

Inherits any biases from the base Gemma 3 270M model.

Framework versions

TRL: 0.21.0
Transformers: 4.55.1
Pytorch: 2.6.0+cu124
Datasets: 4.0.0
Tokenizers: 0.21.4

Citations

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}
@article{gemma_2025,
    title={Gemma 3},
    url={https://arxiv.org/abs/2503.19786},
    publisher={Google DeepMind},
    author={Gemma Team},
    year={2025}
}