first version of the tokenzier and model trained on 24K titles with 8 labels - multi-classification

scibert-title-topics/config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "model",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Artificial intelligence",
+    "1": "Computer science",
+    "2": "Economics",
+    "3": "Engineering",
+    "4": "Mathematics",
+    "5": "Medicine",
+    "6": "Psychology",
+    "7": "Sociology"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Artificial intelligence": 0,
+    "Computer science": 1,
+    "Economics": 2,
+    "Engineering": 3,
+    "Mathematics": 4,
+    "Medicine": 5,
+    "Psychology": 6,
+    "Sociology": 7
+  },
+  "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",
+  "transformers_version": "4.4.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31090
+}

scibert-title-topics/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:732e3a71c73fd33181b5e376f9edb0df5de681c31a002a0e4e0cbd94a08d4cfc
+size 439783011

scibert-title-topics/special_tokens_map.json

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

scibert-title-topics/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": null, "special_tokens_map_file": null, "name_or_path": "model"}