Upload 6 files

README.md

@@ -1,3 +1,69 @@
 ---
+language: zh
+tags:
+- bert
+- multilabel-classification
+- chinese
+- intent-classification
+- time-lbs
 license: mit
 ---
+
+# 中文多标签意图识别模型（BERT）
+
+这是一个基于 `bert-base-chinese` 微调的多标签分类模型，支持以下任务：
+
+对中文query进行分类
+- 多分类：意图识别（chat / simple question / complex question）
+- 二分类：是否时间相关、是否位置（LBS）相关
+
+## 模型结构
+
+- 基础模型：[`bert-base-chinese`](https://huggingface.co/bert-base-chinese)
+- 输出层：一个 5 维的 sigmoid 多标签输出向量
+  - `[意图-chat, 意图-simple, 意图-complex, 是否时间相关, 是否LBS相关]`
+
+## 使用方法
+
+```python
+import torch
+from transformers import BertTokenizer
+from bert_classifier_3 import BertMultiLabelClassifier
+
+# 加载 tokenizer 和模型
+tokenizer = BertTokenizer.from_pretrained("your-username/bert-multilabel-chinese")
+model = BertMultiLabelClassifier(pretrained_model_path="your-username/bert-multilabel-chinese")
+model.load_state_dict(torch.load("pytorch_model.bin", map_location="cpu"))
+model.eval()
+
+# 定义标签
+intent_labels = ["chat", "simple question", "complex question"]
+yesno_labels = ["否", "是"]
+
+# 定义预测函数
+def predict(query):
+    enc = tokenizer(
+        query,
+        truncation=True,
+        padding="max_length",
+        max_length=128,
+        return_tensors="pt"
+    )
+    with torch.no_grad():
+        logits = model(enc["input_ids"], enc["attention_mask"])
+        probs = torch.sigmoid(logits).squeeze(0)
+        intent_index = torch.argmax(probs[:3]).item()
+        is_time = int(probs[3] > 0.5)
+        is_lbs = int(probs[4] > 0.5)
+
+        return {
+            "query": query,
+            "意图": intent_labels[intent_index],
+            "是否时间相关": yesno_labels[is_time],
+            "是否lbs相关": yesno_labels[is_lbs],
+            "原始概率": probs.tolist()
+        }
+
+# 示例查询
+result = predict("明天北京天气怎么样？")
+print(result)

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "type_vocab_size": 2,
+  "vocab_size": 21128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b02f410dda9ca48c233a818e7626d9b23327fa53c872d499bba0a513fedf0a1
+size 210660184

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}