Instructions to use werty1248/Qwen2.5-32B-s1.1-Ko-Native with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use werty1248/Qwen2.5-32B-s1.1-Ko-Native with Transformers:

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

pipe = pipeline("text-generation", model="werty1248/Qwen2.5-32B-s1.1-Ko-Native")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("werty1248/Qwen2.5-32B-s1.1-Ko-Native")
model = AutoModelForCausalLM.from_pretrained("werty1248/Qwen2.5-32B-s1.1-Ko-Native", device_map="auto")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use werty1248/Qwen2.5-32B-s1.1-Ko-Native with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "werty1248/Qwen2.5-32B-s1.1-Ko-Native"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "werty1248/Qwen2.5-32B-s1.1-Ko-Native",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/werty1248/Qwen2.5-32B-s1.1-Ko-Native

SGLang

How to use werty1248/Qwen2.5-32B-s1.1-Ko-Native 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 "werty1248/Qwen2.5-32B-s1.1-Ko-Native" \
    --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": "werty1248/Qwen2.5-32B-s1.1-Ko-Native",
		"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 "werty1248/Qwen2.5-32B-s1.1-Ko-Native" \
        --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": "werty1248/Qwen2.5-32B-s1.1-Ko-Native",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use werty1248/Qwen2.5-32B-s1.1-Ko-Native with Docker Model Runner:
```
docker model run hf.co/werty1248/Qwen2.5-32B-s1.1-Ko-Native
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Korean S1K-1.1

Generation Result: werty1248/qwen-32b-s1.1-Ko-Native-result
- AIME2024(Korean): 30% (9/30) with max_tokens=8192
Chinese appears in think tokens (Not halucination or failure behavior. Solved correctly in Chinese, then answered in Korean)

Training Details

Train with s1k official code
- block_size = 20000
- gradient_checkpointing=True
Training Dataset: werty1248/s1k-1.1-Ko-ReGenerated-Formatted
- Translated questions from s1k-1.1 into Korean, and then regenearted using Deepseek-R1.
- Need to modify "text" column to Qwen format
8x H200 SXM, 2 hours; $63.84, except for the cost of trial and error :(

Evaluation

HRM8K - Korean Math Benchmark

Generated and evaluated with my own code; accuracy may differ.

Model	GSM8K	KSM	MATH	OMNI_MATH
Qwen2.5-32B-s1.1-Ko-Native	89.92	39.85	87.73	42.06
*GPT-4o	91.21	22.83	74.45	30.75
*GPT-4o-mini	87.57	19.40	70.68	26.45
EXAONE-3.5-7.8B-Stratos-Ko	83.02	15.97	67.49	24.62
Qwen2.5-7B-s1.1-Ko-Native	76.27	15.48	66.45	23.57
EXAONE-3.5-7.8B-Instruct	81.58	14.71	63.50	21.69
*Qwen2.5-14B-Instruct	66.34	15.55	53.38	20.64
*Llama-3.1-8B-Instruct	77.79	7.21	49.01	15.92
*Qwen2.5-7B-Instruct	58.38	13.10	48.04	16.55
*EXAONE-3.0-7.8B-Instruct	72.33	7.98	46.79	15.35
*Ko-R1-1.5B-preview	43.3	?	73.1	29.8

* Reported by HRM8K authors

Generation
- temperature = 0.7
- top_p = 0.95
- max_tokens = 8192
- If it exceeded the maximum tokens but did not generate </think> tokens, add </think> tokens and generate 512 additional tokens
Evaluation
- Custom parser & evaluation code; may have parsed incorrectly