Upload 7 files

Add the distilbert model

src/train_bert/topic_classifier_model/config.json

@@ -0,0 +1,62 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Goal 1: End poverty in all its forms everywhere",
+    "1": "Goal 2: Zero Hunger",
+    "2": "Goal 3: Good Health and Well-Being",
+    "3": "Goal 4: Quality Education",
+    "4": "Goal 5: Gender Equality",
+    "5": "Goal 6: Clean Water and Sanitation",
+    "6": "Goal 7: Affordable and Clean Energy",
+    "7": "Goal 8: Decent Work and Economic Growth",
+    "8": "Goal 9: Industries,Innovation, and Infrastructure",
+    "9": "Goal 10: Reduced Inequalities",
+    "10": "Goal 11: Sustainable Cities and Communities",
+    "11": "Goal 12: Responsible Consumption and Production",
+    "12": "Goal 13: Climate Action",
+    "13": "Goal 14: Life Below Water",
+    "14": "Goal 15: Life on Land",
+    "15": "Goal 16: Peace, Justice, and Strong Instiutions",
+    "16": "Goal 17: Partnerships for the Goals"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Goal 10: Reduced Inequalities": 9,
+    "Goal 11: Sustainable Cities and Communities": 10,
+    "Goal 12: Responsible Consumption and Production": 11,
+    "Goal 13: Climate Action": 12,
+    "Goal 14: Life Below Water": 13,
+    "Goal 15: Life on Land": 14,
+    "Goal 16: Peace, Justice, and Strong Instiutions": 15,
+    "Goal 17: Partnerships for the Goals": 16,
+    "Goal 1: End poverty in all its forms everywhere": 0,
+    "Goal 2: Zero Hunger": 1,
+    "Goal 3: Good Health and Well-Being": 2,
+    "Goal 4: Quality Education": 3,
+    "Goal 5: Gender Equality": 4,
+    "Goal 6: Clean Water and Sanitation": 5,
+    "Goal 7: Affordable and Clean Energy": 6,
+    "Goal 8: Decent Work and Economic Growth": 7,
+    "Goal 9: Industries,Innovation, and Infrastructure": 8
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.1",
+  "vocab_size": 30522
+}

src/train_bert/topic_classifier_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:130c8e5deecc14277276719c7c0e24f836eb2ef7ac7558d591ebbdca195bf536
+size 267878708

src/train_bert/topic_classifier_model/special_tokens_map.json

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

src/train_bert/topic_classifier_model/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

src/train_bert/topic_classifier_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:065a3a69c45d460583f6e974780e25e39e359f94094ab3d0d2b20048ff15fb8a
+size 5777