Initial upload housing distilbert classifier

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4354251d8bb7e0403ce9c1acad0d741974e26d4cbb078685cc9fa9de65040c21
+size 265506843

model_class.py

@@ -0,0 +1,21 @@
+import torch
+from torch import nn
+from transformers import DistilBertModel, DistilBertTokenizer
+
+class MultilabelClassifier(nn.Module):
+    """Base model for multilabel classification supporting different backbones"""
+    
+    def __init__(self, model_name, num_labels, dropout=0.1):
+        super(MultilabelClassifier, self).__init__()
+        
+        self.backbone = DistilBertModel.from_pretrained(model_name)
+        self.dropout = nn.Dropout(dropout)
+        self.classifier = nn.Linear(768, num_labels)
+        self.sigmoid = nn.Sigmoid()
+    
+    def forward(self, input_ids, attention_mask):
+        outputs = self.backbone(input_ids=input_ids, attention_mask=attention_mask)
+        pooled_output = outputs.last_hidden_state[:, 0]
+        x = self.dropout(pooled_output)
+        logits = self.classifier(x)
+        return self.sigmoid(logits)

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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}