Instructions to use madcows/siwon-mini-instruct-0626 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use madcows/siwon-mini-instruct-0626 with Transformers:

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

pipe = pipeline("text-generation", model="madcows/siwon-mini-instruct-0626", 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("madcows/siwon-mini-instruct-0626", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("madcows/siwon-mini-instruct-0626", 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 Settings

vLLM

How to use madcows/siwon-mini-instruct-0626 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "madcows/siwon-mini-instruct-0626"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "madcows/siwon-mini-instruct-0626",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/madcows/siwon-mini-instruct-0626

SGLang

How to use madcows/siwon-mini-instruct-0626 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 "madcows/siwon-mini-instruct-0626" \
    --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": "madcows/siwon-mini-instruct-0626",
		"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 "madcows/siwon-mini-instruct-0626" \
        --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": "madcows/siwon-mini-instruct-0626",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use madcows/siwon-mini-instruct-0626 with Docker Model Runner:
```
docker model run hf.co/madcows/siwon-mini-instruct-0626
```

madcows commited on Jul 2, 2025

Commit

ad30761

verified ·

1 Parent(s): 05f6f92

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -0

README.md CHANGED Viewed

@@ -100,6 +100,17 @@ response = tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_speci
 print(response)
 ```
 ## 📌 Caution
 * Commercial use is strictly prohibited.

 print(response)
 ```
+## 📊 Model Performance Comparison
+Performance scores across three Korean language benchmarks (KMMLU, ko_best, pawsx_ko).
+| Model                          | KMMLU (0-shot) | ko_best (5-shot) | pawsx_ko |
+|-------------------------------|----------------|------------------|----------|
+| Phi-4-mini-instruct           | 0.3161         | 0.6341           | 0.5300   |
+| kanana-1.5-2.1b-instruct-2505 | 0.1577         | 0.7165           | 0.5070   |
+| EXAONE-3.5-2.4B-Instruct       | 0.3071         | 0.6496           | 0.5655   |
+| siwon-mini-instruct-0626      | 0.3387         | 0.5576           | 0.5485   |
 ## 📌 Caution
 * Commercial use is strictly prohibited.