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
```

twnlp

nielsr HF Staff commited on about 23 hours ago

Commit

e6d757f

1 Parent(s): 36ce215

Improve model card: add metadata, paper link and library tags (#1)

Browse files

- Improve model card: add metadata, paper link and library tags (ea6dee36066e6108c4872950acd3b945a6eac919)

Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +56 -28

README.md CHANGED Viewed

@@ -1,38 +1,45 @@
 ---
 license: apache-2.0
 ---
-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。
-🔥 项目地址：https://github.com/TW-NLP/ChineseErrorCorrector
-## 模型列表
-| 模型名称                                                                                        | 纠错类型  | 描述                                         |
-|:--------------------------------------------------------------------------------------------|:------|:-------------------------------------------|
-| [twnlp/ChineseErrorCorrector3-4B](https://huggingface.co/twnlp/ChineseErrorCorrector3-4B)   | 语法+拼写 | 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。   |
-| [twnlp/ChineseErrorCorrector2-7B](https://huggingface.co/twnlp/ChineseErrorCorrector2-7B)   | 语法+拼写 | 使用200万纠错数据进行多轮迭代训练，适用于语法纠错和拼写纠错，效果较好。 |
-## 模型评测（NaCGEC Data）
-| Model Name        | Model Link                                                                                                              | Base Model                     | Avg        | SIGHAN-2015 | EC-LAW | MCSC   | GPU | QPS     |
-|:------------------|:------------------------------------------------------------------------------------------------------------------------|:-------------------------------|:-----------|:------------|:-------|:-------|:--------|:--------|
-| Kenlm-CSC         | [shibing624/chinese-kenlm-klm](https://huggingface.co/shibing624/chinese-kenlm-klm)                                     | kenlm                          | 0.3409     | 0.3147      | 0.3763 | 0.3317 | CPU     | 9       |
-| Mengzi-T5-CSC     | [shibing624/mengzi-t5-base-chinese-correction](https://huggingface.co/shibing624/mengzi-t5-base-chinese-correction)     | mengzi-t5-base                 | 0.3984     | 0.7758      | 0.3156 | 0.1039 | GPU     | 214     |
-| ERNIE-CSC         | [PaddleNLP/ernie-csc](https://github.com/PaddlePaddle/PaddleNLP/tree/develop/legacy/examples/text_correction/ernie-csc) | PaddlePaddle/ernie-1.0-base-zh | 0.4353     | 0.8383      | 0.3357 | 0.1318 | GPU     | 114     |
-| MacBERT-CSC       | [shibing624/macbert4csc-base-chinese](https://huggingface.co/shibing624/macbert4csc-base-chinese)                       | hfl/chinese-macbert-base       | 0.3993     | 0.8314      | 0.1610 | 0.2055 | GPU     | **224** |
-| ChatGLM3-6B-CSC   | [shibing624/chatglm3-6b-csc-chinese-lora](https://huggingface.co/shibing624/chatglm3-6b-csc-chinese-lora)               | THUDM/chatglm3-6b              | 0.4538     | 0.6572      | 0.4369 | 0.2672 | GPU     | 3       |
-| Qwen2.5-1.5B-CTC  | [shibing624/chinese-text-correction-1.5b](https://huggingface.co/shibing624/chinese-text-correction-1.5b)               | Qwen/Qwen2.5-1.5B-Instruct     | 0.6802     | 0.3032      | 0.7846 | 0.9529 | GPU     | 6       |
-| Qwen2.5-7B-CTC    | [shibing624/chinese-text-correction-7b](https://huggingface.co/shibing624/chinese-text-correction-7b)                   | Qwen/Qwen2.5-7B-Instruct       | 0.8225     | 0.4917      | 0.9798 | 0.9959 | GPU     | 3       |
-| **Qwen3-4B-CTC(Our)** | [twnlp/ChineseErrorCorrector3-4B](https://huggingface.co/twnlp/ChineseErrorCorrector3-4B)                   | Qwen/Qwen3-4B                  | **0.8521** | 0.6340      | 0.9360 | 0.9864 | GPU     | 5       |
-Without [ChineseErrorCorrector](https://github.com/TW-NLP/ChineseErrorCorrector), you can use the model like this:
-First, you pass your input through the transformer model, then you get the generated sentence.
-Install package:
-```
-pip install transformers
-```
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -69,10 +76,31 @@ generated_ids = [
 response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 print(response)
 ```
-output:
-```shell
-对待每一项工作都要一丝不苟。
 ```

 ---
 license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+language:
+- zh
+base_model: Qwen/Qwen3-4B
+tags:
+- text-correction
+- cgec
+- csc
 ---
+# ChineseErrorCorrector3-4B
+[**🇨🇳中文**](https://github.com/TW-NLP/ChineseErrorCorrector/blob/main/README.md) | [**English**](https://github.com/TW-NLP/ChineseErrorCorrector/blob/main/README_EN.md)
+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](https://huggingface.co/papers/2606.00020).
+- **Project Page:** [ChineseErrorCorrector GitHub](https://github.com/TW-NLP/ChineseErrorCorrector)
+- **Paper:** [arXiv:2606.00020](https://arxiv.org/abs/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��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:
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 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:
+```bibtex
+@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},
+}
 ```