Instructions to use aselbaekki/Qwen2.5-3B-korean-petition-100k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aselbaekki/Qwen2.5-3B-korean-petition-100k with Transformers:

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

pipe = pipeline("text-generation", model="aselbaekki/Qwen2.5-3B-korean-petition-100k")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aselbaekki/Qwen2.5-3B-korean-petition-100k")
model = AutoModelForCausalLM.from_pretrained("aselbaekki/Qwen2.5-3B-korean-petition-100k", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aselbaekki/Qwen2.5-3B-korean-petition-100k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aselbaekki/Qwen2.5-3B-korean-petition-100k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aselbaekki/Qwen2.5-3B-korean-petition-100k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aselbaekki/Qwen2.5-3B-korean-petition-100k

SGLang

How to use aselbaekki/Qwen2.5-3B-korean-petition-100k 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 "aselbaekki/Qwen2.5-3B-korean-petition-100k" \
    --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": "aselbaekki/Qwen2.5-3B-korean-petition-100k",
		"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 "aselbaekki/Qwen2.5-3B-korean-petition-100k" \
        --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": "aselbaekki/Qwen2.5-3B-korean-petition-100k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aselbaekki/Qwen2.5-3B-korean-petition-100k with Docker Model Runner:
```
docker model run hf.co/aselbaekki/Qwen2.5-3B-korean-petition-100k
```

Qwen2.5-3B Korean Petition 100K

Model Details

Model Description

Qwen2.5-3B Korean Petition 100K is a supervised fine-tuned language model based on Qwen2.5-3B. The model was trained on approximately 100,000 Korean public petition samples to improve its ability to understand and generate Korean formal writing, public opinions, and petition-style text.

The model is intended for research purposes and experimentation with Korean language generation and instruction-following tasks.

Developed by: Asel Nurlanbek kyzy
Funded by: Personal research / Korea University of Technology and Education (KOREATECH)
Shared by: aselbaekki
Model type: Causal Language Model
Language(s): Korean
License: Apache 2.0
Finetuned from model: Qwen/Qwen2.5-3B

Model Sources

Repository: https://huggingface.co/aselbaekki/Qwen2.5-3B-korean-petition-100k
Base Model: https://huggingface.co/Qwen/Qwen2.5-3B

Uses

Direct Use

The model can be used for

Korean text generation
Korean instruction following
Petition generation
Text completion
Korean NLP research
Educational purposes

Downstream Use

Possible downstream applications include

Chatbots
Summarization
Question Answering
Writing assistance
Public opinion analysis
Korean document generation

Out-of-Scope Use

This model should not be used for

Medical advice
Legal advice
Financial decision making
Safety-critical applications
Generating misinformation or harmful content

Bias, Risks, and Limitations

The model inherits limitations from the original Qwen2.5-3B model and the petition dataset used during fine-tuning.

Potential limitations include:

Biases present in public petition data
Hallucinated information
Limited factual reliability
Performance degradation outside Korean language tasks

Users should verify important outputs before use.

How to Get Started

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "aselbaekki/Qwen2.5-3B-korean-petition-100k"

tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "대한민국 교육 정책에 대해 설명해주세요."

messages = [
    {"role": "user", "content": prompt}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

inputs = tokenizer(text, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=512
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training Details

Training Data

The model was fine-tuned on approximately 100,000 Korean petition samples.

The dataset consists primarily of Korean public petitions containing formal writing and citizen opinions.

Training Procedure

Preprocessing

Tokenization using the original Qwen2.5 tokenizer
Standard chat template formatting
Sequence truncation and padding

Training Hyperparameters

Parameter	Value
Base Model	Qwen2.5-3B
Epochs	1
Learning Rate	5e-5
Batch Size	4
Gradient Accumulation	4
Scheduler	Cosine
Warmup Ratio	0.03
Precision	BF16
Optimizer	AdamW
Framework	Hugging Face Transformers

Evaluation

The model was qualitatively evaluated on Korean instruction-following and text generation tasks.

Future work will include standardized benchmarks for

Ko-MMLU
KMMLU
Korean instruction-following evaluation
Human evaluation

Technical Specifications

Model Architecture

Architecture: Qwen2ForCausalLM
Parameters: 3 Billion
Context Length: 32K tokens (base model capability)
Framework: Hugging Face Transformers

Compute Infrastructure

Hardware

NVIDIA GPU
BF16 mixed precision

Software

Python
PyTorch
Transformers
Accelerate
Hugging Face Trainer

Citation

If you use this model in your research, please cite both the original Qwen2.5 paper and this repository.

@misc{qwen25-korean-petition-100k,
  author = {Asel Nurlanbek kyzy},
  title = {Qwen2.5-3B Korean Petition 100K},
  year = {2026},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/aselbaekki/Qwen2.5-3B-korean-petition-100k}}
}

Contact

For questions or feedback, please open an issue on the Hugging Face repository or contact the repository owner.

Hugging Face: https://huggingface.co/aselbaekki

Downloads last month: 5

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for aselbaekki/Qwen2.5-3B-korean-petition-100k

Base model

Qwen/Qwen2.5-3B

Finetuned

(521)

this model