Instructions to use twnlp/ChineseErrorCorrector3-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use twnlp/ChineseErrorCorrector3-4B with Transformers:

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

pipe = pipeline("text-generation", model="twnlp/ChineseErrorCorrector3-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("twnlp/ChineseErrorCorrector3-4B")
model = AutoModelForCausalLM.from_pretrained("twnlp/ChineseErrorCorrector3-4B")
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 twnlp/ChineseErrorCorrector3-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "twnlp/ChineseErrorCorrector3-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "twnlp/ChineseErrorCorrector3-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/twnlp/ChineseErrorCorrector3-4B

SGLang

How to use twnlp/ChineseErrorCorrector3-4B 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 "twnlp/ChineseErrorCorrector3-4B" \
    --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": "twnlp/ChineseErrorCorrector3-4B",
		"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 "twnlp/ChineseErrorCorrector3-4B" \
        --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": "twnlp/ChineseErrorCorrector3-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use twnlp/ChineseErrorCorrector3-4B with Docker Model Runner:
```
docker model run hf.co/twnlp/ChineseErrorCorrector3-4B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

ChineseErrorCorrector3-4B

🇨🇳中文 | English

ChineseErrorCorrector3-4B is part of a comprehensive platform for Chinese text correction, integrating academic research, model training, evaluation, and inference. It covers two core directions: Spelling Correction (CSC) and Grammatical Error Correction (CGEC).

The methodology behind this line of models is presented in the paper CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards.

Project Page: ChineseErrorCorrector GitHub
Paper: arXiv:2606.00020

模型描述

一个面向中文文本纠错任务的综合平台，集学术研究、模型训练、模型评测和推理部署于一体，覆盖拼写纠错与语法纠错两个核心方向。

twnlp/ChineseErrorCorrector3-4B: 使用200万纠错数据进行全量训练，适用于语法纠错和拼写纠错，效果最好，推荐使用。

模型评测（NaCGEC Data）

Model Name	Base Model	Avg	SIGHAN-2015	EC-LAW	MCSC	GPU	QPS
ChatGLM3-6B-CSC	THUDM/chatglm3-6b	0.4538	0.6572	0.4369	0.2672	GPU	3
Qwen2.5-1.5B-CTC	Qwen/Qwen2.5-1.5B-Instruct	0.6802	0.3032	0.7846	0.9529	GPU	6
Qwen2.5-7B-CTC	Qwen/Qwen2.5-7B-Instruct	0.8225	0.4917	0.9798	0.9959	GPU	3
Qwen3-4B-CTC(Our)	Qwen/Qwen3-4B	0.8521	0.6340	0.9360	0.9864	GPU	5

Sample Usage

You can use the model with the transformers library as follows:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "twnlp/ChineseErrorCorrector3-4B"

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

prompt = "你是一个文本纠错专家，纠正输入句子中的语法错误，并输出正确的句子，输入句子为："
text_input = "对待每一项工作都要一丝不够。"
messages = [
    {"role": "user", "content": prompt + text_input}
]
text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True,
        enable_thinking=False # Switches between thinking and non-thinking modes. Default is True.
    )
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(response)
# Output: 对待每一项工作都要一丝不苟。

Citation

If you find this work helpful, please cite:

@misc{tian2026csrpchainofthoughtreasoningchinese,
      title={CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards}, 
      author={Wei Tian and Yuhao Zhou and Man Lan},
      year={2026},
      eprint={2606.00020},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2606.00020}, 
}

@misc{tian2025chineseerrorcorrector34bstateoftheartchinesespelling,
      title={ChineseErrorCorrector3-4B: State-of-the-Art Chinese Spelling and Grammar Corrector},
      author={Wei Tian and YuhaoZhou},
      year={2025},
      eprint={2511.17562},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2511.17562},
}