Initial upload

LE_detection/config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Career",
+    "1": "Death",
+    "2": "Education",
+    "3": "Financial",
+    "4": "Health",
+    "5": "Identity",
+    "6": "Legal",
+    "7": "Lifestyle_Change",
+    "8": "New_Birth_in_Family",
+    "9": "Relationships_Changes",
+    "10": "Relocation",
+    "11": "Societal"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Career": 0,
+    "Death": 1,
+    "Education": 2,
+    "Financial": 3,
+    "Health": 4,
+    "Identity": 5,
+    "Legal": 6,
+    "Lifestyle_Change": 7,
+    "New_Birth_in_Family": 8,
+    "Relationships_Changes": 9,
+    "Relocation": 10,
+    "Societal": 11
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.32.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

LE_detection/model.py

@@ -0,0 +1,20 @@
+import torch
+from torch import nn
+from transformers import AutoModel, PreTrainedModel, AutoConfig
+
+class BERTDiseaseClassifier(nn.Module):
+    def __init__(self, model_type, num_symps) -> None:
+        super().__init__()
+        self.model_type = model_type
+        self.num_symps = num_symps
+        # multi-label binary classification
+        self.encoder = AutoModel.from_pretrained(model_type)
+        self.dropout = nn.Dropout(self.encoder.config.hidden_dropout_prob)
+        self.clf = nn.Linear(self.encoder.config.hidden_size, num_symps)
+    
+    def forward(self, input_ids=None, attention_mask=None, token_type_ids=None, **kwargs):
+        outputs = self.encoder(input_ids, attention_mask, token_type_ids)
+        x = outputs.last_hidden_state[:, 0, :]   # [CLS] pooling
+        x = self.dropout(x)
+        logits = self.clf(x)
+        return logits

LE_detection/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71150dfb107bda67c29d5e341687789dce8480a19cc83391ff497324168a45d5
+size 1340772783

LE_detection/special_tokens_map.json

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

LE_detection/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

Self-status_determination/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bert-large-uncased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Is_self"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Is_self": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.32.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

Self-status_determination/model.py

@@ -0,0 +1,20 @@
+import torch
+from torch import nn
+from transformers import AutoModel, PreTrainedModel, AutoConfig
+
+class BERTDiseaseClassifier(nn.Module):
+    def __init__(self, model_type, num_symps) -> None:
+        super().__init__()
+        self.model_type = model_type
+        self.num_symps = num_symps
+        # multi-label binary classification
+        self.encoder = AutoModel.from_pretrained(model_type)
+        self.dropout = nn.Dropout(self.encoder.config.hidden_dropout_prob)
+        self.clf = nn.Linear(self.encoder.config.hidden_size, num_symps)
+    
+    def forward(self, input_ids=None, attention_mask=None, token_type_ids=None, **kwargs):
+        outputs = self.encoder(input_ids, attention_mask, token_type_ids)
+        x = outputs.last_hidden_state[:, 0, :]   # [CLS] pooling
+        x = self.dropout(x)
+        logits = self.clf(x)
+        return logits

Self-status_determination/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5021fbf15ee7216b32a149f4f4ca78e03b95cbe5040ef463f22708334cff31d6
+size 1340727727

Self-status_determination/special_tokens_map.json

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

Self-status_determination/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}