Upload tokenizer

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<pad>"
+}

tokenizer.json

@@ -0,0 +1,64 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 24,
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 26,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Whitespace"
+  },
+  "post_processor": null,
+  "decoder": null,
+  "model": {
+    "type": "WordLevel",
+    "vocab": {
+      "r": 0,
+      "u": 1,
+      "f": 2,
+      "l": 3,
+      "d": 4,
+      "b": 5,
+      "R": 6,
+      "RR": 7,
+      "RRR": 8,
+      "U": 9,
+      "UU": 10,
+      "UUU": 11,
+      "F": 12,
+      "FF": 13,
+      "FFF": 14,
+      "L": 15,
+      "LL": 16,
+      "LLL": 17,
+      "D": 18,
+      "DD": 19,
+      "DDD": 20,
+      "B": 21,
+      "BB": 22,
+      "BBB": 23,
+      "<|endoftext|>": 24,
+      "<unk>": 25,
+      "<pad>": 26
+    },
+    "unk_token": "<unk>"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "added_tokens_decoder": {
+    "24": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "26": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}