Upload 6 files

README.md

@@ -1,3 +1,29 @@
 ---
+language: en
 license: apache-2.0
+library_name: transformers
+tags:
+- pharmacy
+- drug-classification
+- onnx
 ---
+
+# 药品分类模型（ONNX格式）
+
+## 模型描述
+BERT-base微调的药品分类模型，转换为ONNX格式
+
+## 使用方式
+```python
+from transformers import AutoTokenizer, pipeline
+from onnxruntime import InferenceSession
+
+tokenizer = AutoTokenizer.from_pretrained("您的用户名/模型名")
+session = InferenceSession("model.onnx")
+
+# 预处理
+inputs = tokenizer("I have a headache", return_tensors="np")
+
+# 推理
+outputs = session.run(None, dict(inputs))
+predicted_id = outputs[0].argmax()

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Albuterol",
+    "1": "Amoxicillin",
+    "2": "Fluoxetine",
+    "3": "Ibuprofen",
+    "4": "Levothyroxine",
+    "5": "Loratadine",
+    "6": "Losartan",
+    "7": "Metformin",
+    "8": "Omeprazole",
+    "9": "Simvastatin"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Albuterol": 0,
+    "Amoxicillin": 1,
+    "Fluoxetine": 2,
+    "Ibuprofen": 3,
+    "Levothyroxine": 4,
+    "Loratadine": 5,
+    "Losartan": 6,
+    "Metformin": 7,
+    "Omeprazole": 8,
+    "Simvastatin": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

drug_classifier.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174ae9c49049970cebb33214d2062d41251ecf549c1148412f0082d1319cedb4
+size 442940830

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": true,
+  "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]"
+}