init upload

relevance_model/config.json

@@ -0,0 +1,93 @@
+{
+  "_name_or_path": "/hpc_stor03/sjtu_home/minghao.lv/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": "Anger_Irritability",
+    "1": "Anxious_Mood",
+    "2": "Autonomic_Respiratory_Cardiovascular_symptoms",
+    "3": "Decreased_energy_tiredness_fatigue",
+    "4": "Depressed_Mood",
+    "5": "Gastrointestinal_symptoms",
+    "6": "Genitourinary_sexual_symptoms",
+    "7": "Hyperactivity_agitation",
+    "8": "Impulsivity",
+    "9": "Inattention",
+    "10": "Suicidal_ideas",
+    "11": "Worthlessness_and_guilty",
+    "12": "avoidance_of_stimuli",
+    "13": "compensatory_behaviors_to_prevent_weight_gain",
+    "14": "compulsions",
+    "15": "diminished_emotional_expression",
+    "16": "risky_behaviors",
+    "17": "drastical_shift_in_mood_and_energy",
+    "18": "fear_of_gaining_weight",
+    "19": "fears_of_being_negatively_evaluated",
+    "20": "flight_of_ideas",
+    "21": "intrusion_symptoms",
+    "22": "loss_of_interest_or_motivation",
+    "23": "more_talktive",
+    "24": "obsession",
+    "25": "panic_fear",
+    "26": "poor_memory",
+    "27": "sleep_disturbance",
+    "28": "somatic_muscle",
+    "29": "Derealization&dissociation",
+    "30": "somatic_symptoms_sensory",
+    "31": "weight_and_appetite_change"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Anger_Irritability": 0,
+    "Anxious_Mood": 1,
+    "Autonomic_Respiratory_Cardiovascular_symptoms": 2,
+    "Decreased_energy_tiredness_fatigue": 3,
+    "Depressed_Mood": 4,
+    "Derealization&dissociation": 29,
+    "Gastrointestinal_symptoms": 5,
+    "Genitourinary_sexual_symptoms": 6,
+    "Hyperactivity_agitation": 7,
+    "Impulsivity": 8,
+    "Inattention": 9,
+    "Suicidal_ideas": 10,
+    "Worthlessness_and_guilty": 11,
+    "avoidance_of_stimuli": 12,
+    "compensatory_behaviors_to_prevent_weight_gain": 13,
+    "compulsions": 14,
+    "diminished_emotional_expression": 15,
+    "drastical_shift_in_mood_and_energy": 17,
+    "fear_of_gaining_weight": 18,
+    "fears_of_being_negatively_evaluated": 19,
+    "flight_of_ideas": 20,
+    "intrusion_symptoms": 21,
+    "loss_of_interest_or_motivation": 22,
+    "more_talktive": 23,
+    "obsession": 24,
+    "panic_fear": 25,
+    "poor_memory": 26,
+    "risky_behaviors": 16,
+    "sleep_disturbance": 27,
+    "somatic_muscle": 28,
+    "somatic_symptoms_sensory": 30,
+    "weight_and_appetite_change": 31
+  },
+  "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
+}

relevance_model/model.py

@@ -0,0 +1,23 @@
+import torch
+from torch import nn
+from transformers import AutoModel, PreTrainedModel, AutoConfig
+
+# 你可以直接复用你原来的类，稍微改一下使其兼容 HF 的 save_pretrained 更好
+# 但为了保持和你训练时完全一致，最简单的就是保留你原本的写法
+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)
+        # 保持和你训练时完全一致的逻辑
+        x = outputs.last_hidden_state[:, 0, :]   # [CLS] pooling
+        x = self.dropout(x)
+        logits = self.clf(x)
+        return logits

relevance_model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6eba915776904acff969aa0d0d9783c4ca201a77c43c312b12b0637809192a4
+size 1340854767

relevance_model/special_tokens_map.json

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

relevance_model/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]"
+}

status_model/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "mental/mental-bert-base-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": 768,
+  "id2label": {
+    "0": "uncertainty"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "uncertainty": 0
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

status_model/model.py

@@ -0,0 +1,19 @@
+import torch
+from torch import nn
+from transformers import AutoModel
+
+class BERTDiseaseClassifier(nn.Module):
+    def __init__(self, model_type, num_symps) -> None:
+        super().__init__()
+        self.model_type = model_type
+        self.num_symps = num_symps
+        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

status_model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9354ffb5cc6245b402257af26070a6bf0a120ce417060c9a03a612e36e71b8b0
+size 438012913

status_model/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

status_model/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": false,
+  "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]"
+}