twnlp/ChineseErrorCorrector3-4B

模型列表

模型名称	纠错类型	描述
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	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	Prec	Rec	F0.5
twnlp/ChineseErrorCorrector3-4B	0.743	0.7294	0.7402
twnlp/ChineseErrorCorrector2-7B	0.5686	0.57	0.5689
HW_TSC_nlpcc2023_cgec(华为)	0.5095	0.3129	0.4526
鱼饼啾啾Plus(北京大学)	0.5708	0.1294	0.3394
CUHK_SU(香港中文大学)	0.3882	0.1558	0.2990

Without 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 

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。