Instructions to use Tiiny/SmallThinker-21BA3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Tiiny/SmallThinker-21BA3B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Tiiny/SmallThinker-21BA3B-Instruct")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Tiiny/SmallThinker-21BA3B-Instruct", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Tiiny/SmallThinker-21BA3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Tiiny/SmallThinker-21BA3B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Tiiny/SmallThinker-21BA3B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Tiiny/SmallThinker-21BA3B-Instruct

SGLang

How to use Tiiny/SmallThinker-21BA3B-Instruct 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 "Tiiny/SmallThinker-21BA3B-Instruct" \
    --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": "Tiiny/SmallThinker-21BA3B-Instruct",
		"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 "Tiiny/SmallThinker-21BA3B-Instruct" \
        --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": "Tiiny/SmallThinker-21BA3B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Tiiny/SmallThinker-21BA3B-Instruct with Docker Model Runner:
```
docker model run hf.co/Tiiny/SmallThinker-21BA3B-Instruct
```

Improve model card: Add paper title and abstract

by nielsr HF Staff - opened Jul 31, 2025

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

-1

Improve model card: Add paper title and abstract6d471e8f

nielsr

Jul 31, 2025

Hello!

I've opened this pull request to improve the model card for SmallThinker.

Currently, the model card links to the paper but does not include the paper's title or abstract directly. To make the model card more comprehensive and provide key information at a glance, I've added a new "Paper" section that contains the full title and abstract of the paper "SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment".

This change enhances the documentation and provides valuable context for users exploring the model on the Hub.

jeremyii

Tiiny AI org Jul 31, 2025

Thank you! :)

jeremyii changed pull request status to merged Jul 31, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment