Upload 8 files

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "[BAST]": 105880,
+  "[PST]": 105879
+}

config.json

@@ -9,20 +9,8 @@
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2",
-    "3": "LABEL_3"
-  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2,
-    "LABEL_3": 3
-  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
@@ -35,10 +23,9 @@
   "pooler_size_per_head": 128,
   "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
+  "transformers_version": "4.30.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 105879
+  "vocab_size": 105881
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfed63a1028e8c4dd83e7629006936fe4ccade1d938afc48caf0fa20fcaab40a
+oid sha256:20505263b4949abfe3f9a3e67166d2333972c87d0a3327ae35bf822cc1700f9f
 size 669510773

special_tokens_map.json

@@ -1,4 +1,8 @@
 {
+  "additional_special_tokens": [
+    "[PST]",
+    "[BAST]"
+  ],
   "cls_token": "[CLS]",
   "mask_token": "[MASK]",
   "pad_token": "[PAD]",

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {
@@ -52,6 +47,24 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 105879,
+      "content": "[PST]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 105880,
+      "content": "[BAST]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -1,12 +1,15 @@
 {
+  "additional_special_tokens": [
+    "[PST]",
+    "[BAST]"
+  ],
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "bert-base-multilingual-uncased",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73c2285cdec4b4c3d4c25068deadd439adc14e8fd4ea6d06c5590577ba43887d
-size 3451
+oid sha256:6138366098da356d2e2619d3560551c4d949ff18fd4428b27b17f87c88f3d0a3
+size 3899