Add Tokenizer config & Update model config

config.json

@@ -3,6 +3,38 @@
     "CharacterBertModel"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "character_embeddings_dim": 16,
+  "cnn_activation": "relu",
+  "cnn_filters": [
+    [
+      1,
+      32
+    ],
+    [
+      2,
+      32
+    ],
+    [
+      3,
+      64
+    ],
+    [
+      4,
+      128
+    ],
+    [
+      5,
+      256
+    ],
+    [
+      6,
+      512
+    ],
+    [
+      7,
+      1024
+    ]
+  ],
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -10,8 +42,12 @@
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
+  "max_word_length": 50,
+  "mlm_vocab_size": 100000,
   "model_type": "character_bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
+  "num_highway_layers": 2,
+  "tie_word_embeddings": false,
   "type_vocab_size": 2
 }

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"max_word_length": 50, "do_lower_case": true, "do_basic_tokenize": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}