Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,3 @@
+{
+  "pad_token": "[PAD]"
+}

tokenizer.json

@@ -0,0 +1,51 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 1,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
+  "added_tokens": [
+    {
+      "id": 11,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Split",
+    "pattern": {
+      "String": ""
+    },
+    "behavior": "Isolated",
+    "invert": false
+  },
+  "post_processor": null,
+  "decoder": null,
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "0": 0,
+      "1": 1,
+      "2": 2,
+      "3": 3,
+      "4": 4,
+      "5": 5,
+      "6": 6,
+      "7": 7,
+      "8": 8,
+      "9": 9,
+      "S": 10
+    },
+    "unk_token": "[UNK]"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "added_tokens_decoder": {
+    "11": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}