Adding AP classifier

AP/ap_model_comprehensive_evaluation.json

@@ -0,0 +1,10 @@
+{
+    "accuracy": 0.9925,
+    "precision": 0.9926111569879937,
+    "recall": 0.9925,
+    "f1_score": 0.9925235843292519,
+    "roc_auc": 0.9991309694609551,
+    "mcc": 0.9805321551999564,
+    "log_loss": 0.039218558579236416,
+    "classification_report": "              precision    recall  f1-score   support\n\n      Not AP       1.00      0.99      0.99       595\n          AP       0.98      1.00      0.99       205\n\n    accuracy                           0.99       800\n   macro avg       0.99      0.99      0.99       800\nweighted avg       0.99      0.99      0.99       800\n"
+}

AP/config.json

@@ -0,0 +1,26 @@
+{
+  "_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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.48.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

AP/model_card.json

@@ -0,0 +1,11 @@
+{
+    "model_name": "AP Classifier BERT",
+    "description": "BERT model trained to classify if an article is from AP.",
+    "training_data": "Custom dataset of labeled news articles.",
+    "metrics": "See 'ap_model_comprehensive_evaluation.json' for full evaluation metrics.",
+    "tags": [
+        "news classification",
+        "BERT",
+        "AP"
+    ]
+}

AP/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99906c8b7c290d3f36827f705a44fbc00a7f9e0f8d33841076ad48486379439a
+size 661690424

AP/special_tokens_map.json

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

AP/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]"
+}