Instructions to use twnlp/ChineseErrorCorrector4-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use twnlp/ChineseErrorCorrector4-4B with Transformers:

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

pipe = pipeline("text-generation", model="twnlp/ChineseErrorCorrector4-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("twnlp/ChineseErrorCorrector4-4B")
model = AutoModelForCausalLM.from_pretrained("twnlp/ChineseErrorCorrector4-4B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use twnlp/ChineseErrorCorrector4-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "twnlp/ChineseErrorCorrector4-4B"
# 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/ChineseErrorCorrector4-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/twnlp/ChineseErrorCorrector4-4B

SGLang

How to use twnlp/ChineseErrorCorrector4-4B 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/ChineseErrorCorrector4-4B" \
    --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/ChineseErrorCorrector4-4B",
		"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/ChineseErrorCorrector4-4B" \
        --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/ChineseErrorCorrector4-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use twnlp/ChineseErrorCorrector4-4B with Docker Model Runner:
```
docker model run hf.co/twnlp/ChineseErrorCorrector4-4B
```

Add library_name metadata

by nielsr HF Staff - opened 1 day ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+40

-59

Files changed (1) hide show

README.md +40 -59

README.md CHANGED Viewed

@@ -1,44 +1,45 @@
 ---
-language:
-  - zh
-license: apache-2.0
-tags:
-  - chinese
-  - text-correction
-  - grammatical-error-correction
-  - spelling-check
-  - qwen3
-  - chain-of-thought
-  - reinforcement-learning
 base_model: Qwen/Qwen3-4B
 datasets:
-  - twnlp/ChineseErrorCorrector
 metrics:
-  - f1
-  - precision
-  - recall
 pipeline_tag: text-generation
 model-index:
-  - name: ChineseErrorCorrector4-4B
-    results:
-      - task:
-          type: text-generation
-          name: Chinese Grammatical Error Correction
-        dataset:
-          name: NACGEC
-          type: nacgec
-        metrics:
-          - type: f0.5
-            value: 50.99
-      - task:
-          type: text-generation
-          name: Chinese Spelling Check
-        dataset:
-          name: CSCD
-          type: cscd
-        metrics:
-          - type: f1
-            value: 59.61
 ---
 # ChineseErrorCorrector4-4B (CSRP)
@@ -59,6 +60,8 @@ model-index:
 ---
 ## 🔥 Recent Updates
 | Date | Update |
@@ -70,7 +73,7 @@ model-index:
 ## 💡 Introduction
-**ChineseErrorCorrector4-4B** is a high-precision Chinese Grammatical Error Correction (CGEC) and Chinese Spelling Check (CSC) model, built on the **CSRP (CPT → SFT → RL)** three-stage training framework.
 ### The Problem: Over-Correction Bias
@@ -98,10 +101,6 @@ Traditional LLM-based correction systems often suffer from **over-correction bia
 | CEC3 (4B) | 54.20 | 34.75 | 48.74 |
 | **CSRP (4B) [Ours]** ✅ | **57.17** | **35.60** | **50.99** |
-> 🔥 **超越 14B 大模型：** 参数量仅为三成，$F_{0.5}$ 相比 ScholarGEC-14B 提升 **+3.64**！
->
-> 🔥 **极高准确率 (Precision 57.17%)：** 远超其他模型，最大程度压制了 false-positive（假阳性改写），真正做到"**无错不改，有错必精**"。
 ---
 ### 榜单二：中文拼写检查（CSC）— CSCD 基准
@@ -199,24 +198,6 @@ print(response)
 下个星期，我跟我朋友打算去法国玩儿。
 ```
-**Supported error types:**
-| 错误类型 | 说明 |
-|---------|------|
-| 错别字 | Typos / wrong characters |
-| 词语搭配错误 | Wrong word collocation |
-| 词性错误 | Wrong part of speech |
-| 语序错误 | Wrong word order |
-| 成分残缺 | Missing sentence components |
-| 成分赘余 | Redundant components |
-| 关联词使用错误 | Wrong conjunction usage |
-| 指代不明 | Ambiguous reference |
-| 语义逻辑不通 | Semantic/logical inconsistency |
-| 无误 | No error |
----
 ---
 ## 📜 License
@@ -237,4 +218,4 @@ This project is released under the [Apache 2.0 License](LICENSE).
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2606.00020},
 }
-```

 ---
 base_model: Qwen/Qwen3-4B
 datasets:
+- twnlp/ChineseErrorCorrector
+language:
+- zh
+license: apache-2.0
 metrics:
+- f1
+- precision
+- recall
 pipeline_tag: text-generation
+library_name: transformers
+tags:
+- chinese
+- text-correction
+- grammatical-error-correction
+- spelling-check
+- qwen3
+- chain-of-thought
+- reinforcement-learning
 model-index:
+- name: ChineseErrorCorrector4-4B
+  results:
+  - task:
+      type: text-generation
+      name: Chinese Grammatical Error Correction
+    dataset:
+      name: NACGEC
+      type: nacgec
+    metrics:
+    - type: f0.5
+      value: 50.99
+  - task:
+      type: text-generation
+      name: Chinese Spelling Check
+    dataset:
+      name: CSCD
+      type: cscd
+    metrics:
+    - type: f1
+      value: 59.61
 ---
 # ChineseErrorCorrector4-4B (CSRP)
 ---
+**ChineseErrorCorrector4-4B** is a high-precision Chinese Grammatical Error Correction (CGEC) and Chinese Spelling Check (CSC) model, 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).
 ## 🔥 Recent Updates
 | Date | Update |
 ## 💡 Introduction
+**ChineseErrorCorrector4-4B** is built on the **CSRP (CPT → SFT → RL)** three-stage training framework.
 ### The Problem: Over-Correction Bias
 | CEC3 (4B) | 54.20 | 34.75 | 48.74 |
 | **CSRP (4B) [Ours]** ✅ | **57.17** | **35.60** | **50.99** |
 ---
 ### 榜单二：中文拼写检查（CSC）— CSCD 基准
 下个星期，我跟我朋友打算去法国玩儿。
 ```
 ---
 ## 📜 License
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2606.00020},
 }
+```