Upload Blt model converted

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc3d4af0b585afb391e60bd5eae3c37d7423ea44c08250a5e17c41031fe91587
-size 21306236008
+oid sha256:a46dae2cb16f07166d00bc6e75b7b6f28a3bea216d456294d1b0e8ccf5aea999
+size 28986266224

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,377 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 1,
+      "content": "<s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "</s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 260,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "<s>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "SpecialToken": {
+          "id": "<s>",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "<s>": {
+        "id": "<s>",
+        "ids": [
+          1
+        ],
+        "tokens": [
+          "<s>"
+        ]
+      }
+    }
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": "",
+    "end_of_word_suffix": "",
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "<boe>": 0,
+      "<s>": 1,
+      "</s>": 2,
+      "<pad>": 3,
+      "Ā": 4,
+      "ā": 5,
+      "Ă": 6,
+      "ă": 7,
+      "Ą": 8,
+      "ą": 9,
+      "Ć": 10,
+      "ć": 11,
+      "Ĉ": 12,
+      "ĉ": 13,
+      "Ċ": 14,
+      "ċ": 15,
+      "Č": 16,
+      "č": 17,
+      "Ď": 18,
+      "ď": 19,
+      "Đ": 20,
+      "đ": 21,
+      "Ē": 22,
+      "ē": 23,
+      "Ĕ": 24,
+      "ĕ": 25,
+      "Ė": 26,
+      "ė": 27,
+      "Ę": 28,
+      "ę": 29,
+      "Ě": 30,
+      "ě": 31,
+      "Ĝ": 32,
+      "ĝ": 33,
+      "Ğ": 34,
+      "ğ": 35,
+      "Ġ": 36,
+      "!": 37,
+      "\"": 38,
+      "#": 39,
+      "$": 40,
+      "%": 41,
+      "&": 42,
+      "'": 43,
+      "(": 44,
+      ")": 45,
+      "*": 46,
+      "+": 47,
+      ",": 48,
+      "-": 49,
+      ".": 50,
+      "/": 51,
+      "0": 52,
+      "1": 53,
+      "2": 54,
+      "3": 55,
+      "4": 56,
+      "5": 57,
+      "6": 58,
+      "7": 59,
+      "8": 60,
+      "9": 61,
+      ":": 62,
+      ";": 63,
+      "<": 64,
+      "=": 65,
+      ">": 66,
+      "?": 67,
+      "@": 68,
+      "A": 69,
+      "B": 70,
+      "C": 71,
+      "D": 72,
+      "E": 73,
+      "F": 74,
+      "G": 75,
+      "H": 76,
+      "I": 77,
+      "J": 78,
+      "K": 79,
+      "L": 80,
+      "M": 81,
+      "N": 82,
+      "O": 83,
+      "P": 84,
+      "Q": 85,
+      "R": 86,
+      "S": 87,
+      "T": 88,
+      "U": 89,
+      "V": 90,
+      "W": 91,
+      "X": 92,
+      "Y": 93,
+      "Z": 94,
+      "[": 95,
+      "\\": 96,
+      "]": 97,
+      "^": 98,
+      "_": 99,
+      "`": 100,
+      "a": 101,
+      "b": 102,
+      "c": 103,
+      "d": 104,
+      "e": 105,
+      "f": 106,
+      "g": 107,
+      "h": 108,
+      "i": 109,
+      "j": 110,
+      "k": 111,
+      "l": 112,
+      "m": 113,
+      "n": 114,
+      "o": 115,
+      "p": 116,
+      "q": 117,
+      "r": 118,
+      "s": 119,
+      "t": 120,
+      "u": 121,
+      "v": 122,
+      "w": 123,
+      "x": 124,
+      "y": 125,
+      "z": 126,
+      "{": 127,
+      "|": 128,
+      "}": 129,
+      "~": 130,
+      "ġ": 131,
+      "Ģ": 132,
+      "ģ": 133,
+      "Ĥ": 134,
+      "ĥ": 135,
+      "Ħ": 136,
+      "ħ": 137,
+      "Ĩ": 138,
+      "ĩ": 139,
+      "Ī": 140,
+      "ī": 141,
+      "Ĭ": 142,
+      "ĭ": 143,
+      "Į": 144,
+      "į": 145,
+      "İ": 146,
+      "ı": 147,
+      "IJ": 148,
+      "ij": 149,
+      "Ĵ": 150,
+      "ĵ": 151,
+      "Ķ": 152,
+      "ķ": 153,
+      "ĸ": 154,
+      "Ĺ": 155,
+      "ĺ": 156,
+      "Ļ": 157,
+      "ļ": 158,
+      "Ľ": 159,
+      "ľ": 160,
+      "Ŀ": 161,
+      "ŀ": 162,
+      "Ł": 163,
+      "ł": 164,
+      "¡": 165,
+      "¢": 166,
+      "£": 167,
+      "¤": 168,
+      "¥": 169,
+      "¦": 170,
+      "§": 171,
+      "¨": 172,
+      "©": 173,
+      "ª": 174,
+      "«": 175,
+      "¬": 176,
+      "Ń": 177,
+      "®": 178,
+      "¯": 179,
+      "°": 180,
+      "±": 181,
+      "²": 182,
+      "³": 183,
+      "´": 184,
+      "µ": 185,
+      "¶": 186,
+      "·": 187,
+      "¸": 188,
+      "¹": 189,
+      "º": 190,
+      "»": 191,
+      "¼": 192,
+      "½": 193,
+      "¾": 194,
+      "¿": 195,
+      "À": 196,
+      "Á": 197,
+      "Â": 198,
+      "Ã": 199,
+      "Ä": 200,
+      "Å": 201,
+      "Æ": 202,
+      "Ç": 203,
+      "È": 204,
+      "É": 205,
+      "Ê": 206,
+      "Ë": 207,
+      "Ì": 208,
+      "Í": 209,
+      "Î": 210,
+      "Ï": 211,
+      "Ð": 212,
+      "Ñ": 213,
+      "Ò": 214,
+      "Ó": 215,
+      "Ô": 216,
+      "Õ": 217,
+      "Ö": 218,
+      "×": 219,
+      "Ø": 220,
+      "Ù": 221,
+      "Ú": 222,
+      "Û": 223,
+      "Ü": 224,
+      "Ý": 225,
+      "Þ": 226,
+      "ß": 227,
+      "à": 228,
+      "á": 229,
+      "â": 230,
+      "ã": 231,
+      "ä": 232,
+      "å": 233,
+      "æ": 234,
+      "ç": 235,
+      "è": 236,
+      "é": 237,
+      "ê": 238,
+      "ë": 239,
+      "ì": 240,
+      "í": 241,
+      "î": 242,
+      "ï": 243,
+      "ð": 244,
+      "ñ": 245,
+      "ò": 246,
+      "ó": 247,
+      "ô": 248,
+      "õ": 249,
+      "ö": 250,
+      "÷": 251,
+      "ø": 252,
+      "ù": 253,
+      "ú": 254,
+      "û": 255,
+      "ü": 256,
+      "ý": 257,
+      "þ": 258,
+      "ÿ": 259
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -1,9 +1,13 @@
 {
-  "tokenizer_class": "BltTokenizer",
+  "tokenizer_class": "PreTrainedTokenizerFast",
   "vocab_size": 260,
   "model_max_length": 1024,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
   "add_bos_token": true,
-  "add_eos_token": false,
+  "add_eos_token": true,
   "bos_token": "<s>",
   "eos_token": "</s>",
   "pad_token": "<pad>",