add tokenizer to main

tokenizer.json

@@ -0,0 +1,57 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "post_processor": null,
+  "decoder": null,
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "vocab": {
+      "<|endoftext|>": 0,
+      " A": 1,
+      " B": 2,
+      " C": 3,
+      " D": 4,
+      " E": 5,
+      " F": 6,
+      " G": 7,
+      " H": 8,
+      " I": 9,
+      " J": 10,
+      " K": 11,
+      " L": 12,
+      " M": 13,
+      " N": 14,
+      " O": 15,
+      " P": 16,
+      " Q": 17,
+      " R": 18,
+      " S": 19,
+      " T": 20,
+      " U": 21,
+      " V": 22,
+      " W": 23,
+      " X": 24,
+      " Y": 25,
+      " Z": 26,
+      " a": 27,
+      " b": 28,
+      " c": 29,
+      " d": 30
+    },
+    "merges": []
+  }
+}