Instructions to use WithinUsAI/Qwen3-Sushi.Math.Code.Expert-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WithinUsAI/Qwen3-Sushi.Math.Code.Expert-0.6B with Transformers:

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

pipe = pipeline("text-generation", model="WithinUsAI/Qwen3-Sushi.Math.Code.Expert-0.6B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WithinUsAI/Qwen3-Sushi.Math.Code.Expert-0.6B")
model = AutoModelForCausalLM.from_pretrained("WithinUsAI/Qwen3-Sushi.Math.Code.Expert-0.6B")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use WithinUsAI/Qwen3-Sushi.Math.Code.Expert-0.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WithinUsAI/Qwen3-Sushi.Math.Code.Expert-0.6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WithinUsAI/Qwen3-Sushi.Math.Code.Expert-0.6B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WithinUsAI/Qwen3-Sushi.Math.Code.Expert-0.6B

SGLang

How to use WithinUsAI/Qwen3-Sushi.Math.Code.Expert-0.6B 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 "WithinUsAI/Qwen3-Sushi.Math.Code.Expert-0.6B" \
    --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": "WithinUsAI/Qwen3-Sushi.Math.Code.Expert-0.6B",
		"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 "WithinUsAI/Qwen3-Sushi.Math.Code.Expert-0.6B" \
        --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": "WithinUsAI/Qwen3-Sushi.Math.Code.Expert-0.6B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WithinUsAI/Qwen3-Sushi.Math.Code.Expert-0.6B with Docker Model Runner:
```
docker model run hf.co/WithinUsAI/Qwen3-Sushi.Math.Code.Expert-0.6B
```

gss1147 commited on Feb 1

Commit

a1a459d

verified ·

1 Parent(s): c155010

Update README.md

Browse files

https://cdn-uploads.huggingface.co/production/uploads/6758f77450b6c087c2c281e1/tir_75qQIJjqbE-HJ9woD.mp4

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -193,4 +193,4 @@ if __name__ == "__main__":
         print("AI Response:", response)
     db_conn.close()
-```

         print("AI Response:", response)
     db_conn.close()
+``''