Initial upload: fine-tuned Topic Classification for SDD pipeline

config.json

@@ -0,0 +1,73 @@
+{
+  "_num_labels": 5,
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "decoder_start_token_id": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "eos_token_id": null,
+  "finetuning_task": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Budaya",
+    "1": "Ekonomi",
+    "2": "Entertainment",
+    "3": "HukumDanKriminal",
+    "4": "Kesehatan",
+    "5": "Lifestyle",
+    "6": "Otomotif",
+    "7": "Pendidikan",
+    "8": "Politik",
+    "9": "Sport",
+    "10": "Tekno",
+    "11": "Wisata",
+    "12": "Lainnya"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "Budaya": 0,
+    "Ekonomi": 1,
+    "Entertainment": 2,
+    "HukumDanKriminal": 3,
+    "Kesehatan": 4,
+    "Lainnya": 12,
+    "Lifestyle": 5,
+    "Otomotif": 6,
+    "Pendidikan": 7,
+    "Politik": 8,
+    "Sport": 9,
+    "Tekno": 10,
+    "Wisata": 11
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "prefix": null,
+  "pruned_heads": {},
+  "task_specific_params": null,
+  "tie_word_embeddings": true,
+  "torchscript": false,
+  "transformers_version": "5.12.1",
+  "type_vocab_size": 2,
+  "use_bfloat16": false,
+  "use_cache": false,
+  "vocab_size": 50000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb613b2dc7a06168586622255ac1177e0e01e7c707e71ce4fc2cfc8f0c9f646
+size 497828908

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:989327840867b00e34b76987e7ae73caf9faaa1b2c9b7ec52b2db8f6404141f5
+size 5201