Upload BERT hierarchical classification model for grades 1, 2 and 3

README.md

@@ -0,0 +1,26 @@
+
+# BERT Hierarchical Classification Model
+
+This model is a fine-tuned BERT-based model for hierarchical classification of Common Core Standard questions.
+
+## Model Description
+
+The model classifies input texts into the following hierarchical levels:
+
+- Grade
+- Domain
+- Cluster
+- Standard
+
+## Files
+
+- `config.json`: Model configuration.
+- `pytorch_model.bin`: Model weights.
+- `modeling.py`: Model class definition.
+- `tokenizer/`: Tokenizer files.
+- `label_encoders.joblib`: Label encoders for mapping predictions back to labels.
+
+## Usage
+
+See instructions below on how to load and use the model.
+

best_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:264a0736580bdc21f02adf05f262b6bb233a7457df11fa950743f6a6abaf6afa
+size 438388429

config.json

@@ -0,0 +1,24 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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_clusters": 20,
+  "num_domains": 8,
+  "num_grades": 9,
+  "num_hidden_layers": 12,
+  "num_standards": 85,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.48.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

label_encoders.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa3a8cc65c51b62af563d2614004a8f84d785b52e40db031e4f7e80230b1259d
+size 2962

modeling.py

@@ -0,0 +1,33 @@
+
+import torch
+import torch.nn as nn
+from transformers import BertModel, BertConfig
+
+class BertHierarchicalClassification(nn.Module):
+    def __init__(self, config):
+        super(BertHierarchicalClassification, self).__init__()
+        self.bert = BertModel(config)
+        hidden_size = config.hidden_size
+
+        self.num_grades = config.num_grades
+        self.num_domains = config.num_domains
+        self.num_clusters = config.num_clusters
+        self.num_standards = config.num_standards
+
+        self.grade_classifier = nn.Linear(hidden_size, self.num_grades)
+        self.domain_classifier = nn.Linear(hidden_size, self.num_domains)
+        self.cluster_classifier = nn.Linear(hidden_size, self.num_clusters)
+        self.standard_classifier = nn.Linear(hidden_size, self.num_standards)
+        self.dropout = nn.Dropout(0.1)
+
+    def forward(self, input_ids, attention_mask):
+        outputs = self.bert(input_ids=input_ids, attention_mask=attention_mask)
+        pooled_output = outputs.pooler_output
+        pooled_output = self.dropout(pooled_output)
+
+        grade_logits = self.grade_classifier(pooled_output)
+        domain_logits = self.domain_classifier(pooled_output)
+        cluster_logits = self.cluster_classifier(pooled_output)
+        standard_logits = self.standard_classifier(pooled_output)
+
+        return grade_logits, domain_logits, cluster_logits, standard_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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}