Update README.md

README.md

@@ -9,6 +9,11 @@ base_model:
 - Qwen/Qwen2.5-0.5B
 ---
 # Qwen2.5-med-book-main-classification
+
+[[中文]](#chinese)    [[English]](#english)
+
+<a id="english"></a>
+
 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
@@ -72,6 +77,84 @@ model = AutoModelForSequenceClassification.from_pretrained(
 )
 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']
+```
+
+# Qwen2.5-med-book-main-classification
+
+[[中文]](#chinese)    [[English]](#english)
+
+<a id="chinese"></a>
+
+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()}