---
license: apache-2.0
language:
- zh
metrics:
- accuracy
- precision
base_model:
- Qwen/Qwen2.5-0.5B
---

<a id="english"></a>

# Qwen2.5-med-book-main-classification

[[中文]](#chinese)    [[English]](#english)



The model is an intermediate product of the [EPCD (Easy-Data-Clean-Pipeline)](https://github.com/ytzfhqs/EDCP) project, primarily used to distinguish between the main content and non-content (such as book introductions, publisher information, writing standards, revision notes) of **medical textbooks** after performing OCR using [MinerU](https://github.com/opendatalab/MinerU). The base model uses [Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B), avoiding the length limitation of the Bert Tokenizer while providing higher accuracy.

# Data Composition

- The data consists of scanned PDF copies of textbooks, converted into `Markdown` files through `OCR` using [MinerU](https://github.com/opendatalab/MinerU). After a simple regex-based cleaning, the samples were split using `\n`, and a `Bloom` probabilistic filter was used for precise deduplication, resulting in 50,000 samples. Due to certain legal considerations, we may not plan to make the dataset publicly available.
- Due to the nature of textbooks, most samples are main content. According to statistics, in our dataset, 79.89% (40,000) are main content samples, while 20.13% (10,000) are non-content samples. Considering data imbalance, we evaluate the model's performance on both Precision and Accuracy metrics on the test set.
- To ensure consistency in the data distribution between the test set and the training set, we used stratified sampling to select 10% of the data as the test set.

# Training Techniques

- To maximize model accuracy, we used Bayesian optimization (TPE algorithm) and Hyperband pruning (HyperbandPruner) to accelerate hyperparameter tuning.

# Model Performance

| Dataset | Accuracy | Precision |
|---------|----------|-----------|
| Train   | 0.9894   | 0.9673    |
| Test    | 0.9788   | 0.9548    |

# Usage

```python
import torch
from transformers import AutoModelForSequenceClassification
from transformers import AutoTokenizer

ID2LABEL = {0: "正文", 1: "非正文"}

model_name = 'ytzfhqs/Qwen2.5-med-book-main-classification'
model = AutoModelForSequenceClassification.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

text = '下列为修订说明'
encoding = tokenizer(text, return_tensors='pt')
encoding = {k: v.to(model.device) for k, v in encoding.items()}
outputs = model(**encoding)
logits = outputs.logits
id = torch.argmax(logits, dim=-1).item()
response = ID2LABEL[id]
print(response)
# "非正文"
```

# For Batch Usage
```python
import torch
from transformers import AutoModelForSequenceClassification
from transformers import AutoTokenizer

ID2LABEL = {0: "正文", 1: "非正文"}

model_name = 'ytzfhqs/Qwen2.5-med-book-main-classification'
model = AutoModelForSequenceClassification.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name, padding_side="left")

text = ['下列为修订说明','阴离子间隙是一项受到广泛重视的酸碱指标。AG是一个计算值，指血浆中未测定的阴离子与未测定的阳离子的差值，正常机体血浆中的阳离子与阴离子总量相等，均为151mmol/L，从而维持电荷平衡。']
encoding = tokenizer(text, return_tensors='pt',padding=True)
encoding = {k: v.to(model.device) for k, v in encoding.items()}
outputs = model(**encoding)
logits = outputs.logits
ids = torch.argmax(logits, dim=-1).tolist()
response = [ID2LABEL[id] for id in ids]
print(response)
# ['非正文', '正文']
```

<a id="chinese"></a>

# Qwen2.5-med-book-main-classification

[[中文]](#chinese)    [[English]](#english)


该模型为[EPCD(Easy-Data-Clean-Pipeline)](https://github.com/ytzfhqs/EDCP)项目的中间产物，主要用来区分使用[MinerU](https://github.com/opendatalab/MinerU)进行OCR后的**医学教科书**的正文与非正文（书本简介、出版社信息、编写规范、修订说明）样本。基础模型使用[Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B)，避免了Bert Tokenizer长度的限制，并且提供了更高的精度。

# 数据组成

 - 数据由教科书PDF扫描件，经过[MinerU](https://github.com/opendatalab/MinerU)进行`OCR`后生成的`Markdown`文件。经过简单的正则化清洗，使用`\n`进行分割样本，经过`Bloom`概率过滤器精准去重，最终产生了5W条样本。由于涉及一些法律条款，我们可能没有计划公开数据集。
 - 由于教科书的特性，样本大多为正文样本，根据统计，在我们的数据集中，正文样本占总样本的79.89%（4W条），非正文样本占总样本的20.13%（1W条）。由于数据的不平衡性，我们综合考虑模型在测试集上的Precision和Accuracy指标。
 - 为了保证测试集与训练集数据分布一致，我们使用分层抽样，选取10%的数据构成测试集。

 # 训练技巧
 - 为了尽可能提高模型精度，我们使用了贝叶斯优化（TPE算法）和Hyperband修剪器（HyperbandPruner）加快模型调参效率。

 # 模型表现
| Dataset | Accuracy | Precision |
|---------|----------|-----------|
| Train   | 0.9894   | 0.9673    |
| Test    | 0.9788   | 0.9548    |

# Usage

```python
import torch
from transformers import AutoModelForSequenceClassification
from transformers import AutoTokenizer

ID2LABEL = {0: "正文", 1: "非正文"}

model_name = 'ytzfhqs/Qwen2.5-med-book-main-classification'
model = AutoModelForSequenceClassification.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

text = '下列为修订说明'
encoding = tokenizer(text, return_tensors='pt')
encoding = {k: v.to(model.device) for k, v in encoding.items()}
outputs = model(**encoding)
logits = outputs.logits
id = torch.argmax(logits, dim=-1).item()
response = ID2LABEL[id]
print(response)
# "非正文"
```

# For Batch Usage
```python
import torch
from transformers import AutoModelForSequenceClassification
from transformers import AutoTokenizer

ID2LABEL = {0: "正文", 1: "非正文"}

model_name = 'ytzfhqs/Qwen2.5-med-book-main-classification'
model = AutoModelForSequenceClassification.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name, padding_side="left")

text = ['下列为修订说明','阴离子间隙是一项受到广泛重视的酸碱指标。AG是一个计算值，指血浆中未测定的阴离子与未测定的阳离子的差值，正常机体血浆中的阳离子与阴离子总量相等，均为151mmol/L，从而维持电荷平衡。']
encoding = tokenizer(text, return_tensors='pt',padding=True)
encoding = {k: v.to(model.device) for k, v in encoding.items()}
outputs = model(**encoding)
logits = outputs.logits
ids = torch.argmax(logits, dim=-1).tolist()
response = [ID2LABEL[id] for id in ids]
print(response)
# ['非正文', '正文']
```