Initial commit of BertModel and tokenizer

config.json

@@ -1,38 +1,34 @@
 {
-  "_num_labels": 5,
-  "architectures": [
-    "BertModel"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "directionality": "bidi",
-  "finetuning_task": "sentiment-analysis",
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "id2label": {
-    "0": "1 star",
-    "1": "2 stars",
-    "2": "3 stars"
-  },
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "label2id": {
-    "1 star": 0,
-    "2 stars": 1,
-    "3 stars": 2
-  },
-  "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",
-  "type_vocab_size": 2,
-  "vocab_size": 105879
-}
+    "architectures": [
+      "BertForSequenceClassification"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "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,
+    "type_vocab_size": 2,
+    "vocab_size": 119547, 
+    "model_name_or_path": "bert-base-multilingual-cased",
+    "num_labels": 3,
+    "finetuning_task": "text_classification",
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1",
+      "2": "LABEL_2"
+    },
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1,
+      "LABEL_2": 2
+    }
+  }
+