Update README.md

README.md

@@ -1,3 +1,44 @@
----
-license: gpl-3.0
----
+---
+license: gpl-3.0
+widget:
+- text: 宵凉百念集孤灯，暗雨鸣廊睡未能。生计坐怜秋一叶，归程冥想浪千层。寒心国事浑难料，堆眼官资信可憎。此去梦中应不忘，顺承门内近觚棱。
+pipeline_tag: text-classification
+---
+
+使用方法如下：
+```python
+from transformers import BertTokenizer, BertForSequenceClassification
+import torch
+
+# 加载已训练的模型和分词器
+model_path = 'qixun/tangsong_qilv_classify'
+tokenizer = BertTokenizer.from_pretrained(model_path)
+model = BertForSequenceClassification.from_pretrained(model_path)
+
+# 预处理函数
+def preprocess_text(text):
+    inputs = tokenizer(text, padding='max_length', truncation=True, max_length=128, return_tensors='pt')
+    return inputs
+
+# 分类函数
+def classify_text(text):
+    model.eval()  # 切换到评估模式
+    inputs = preprocess_text(text)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    logits = outputs.logits
+    probabilities = torch.softmax(logits, dim=1)
+    predicted_label = torch.argmax(probabilities, dim=1).item()
+    return predicted_label, probabilities
+
+# 示例文本
+text = "宵凉百念集孤灯，暗雨鸣廊睡未能。生计坐怜秋一叶，归程冥想浪千层。寒心国事浑难料，堆眼官资信可憎。此去梦中应不忘，顺承门内近觚棱。"
+
+# 调用分类函数
+predicted_label, probabilities = classify_text(text)
+
+# 输出结果
+print(f"预测标签: {predicted_label}")
+print(f"概率分布: {probabilities}")
+
+```