Upload folder using huggingface_hub

README.md

@@ -1,14 +1,12 @@
 ---
 license: mit
 language:
-- und
+- und  # ISO 639-3 code or "und" if not identifiable
 tags:
 - tokenizer
 - bpe
 - flexitok
 - fineweb2
-datasets:
-- flexitok/mod-arithmetic
 ---
 
 # Byte-Level BPE Tokenizer: numeric (0K)
@@ -48,4 +46,4 @@ tokens = tokenizer.encode("Hello, world!")
 ## Sample Encoding
 | Text | Tokens | Token IDs |
 |------|--------|-----------|
-| `1234500119 mod 67` | `1, 2, 3, 4, 5, 0, 0, 1, 1, 9,  , mod,  , 6, 7` | `8, 9, 10, 11, 12, 7, 7, 8, 8, 16, 6, 4, 6, 13, 14` |
+| `123500119 mod 67` | `1, 2, 3, 5, 0, 0, 1, 1, 9,  , mod,  , 6, 7` | `8, 9, 10, 12, 7, 7, 8, 8, 16, 6, 4, 6, 13, 14` |

tokenizer.json

@@ -1 +1,127 @@
-{"<unk>": [0], "~SPECIAL~ALIGNED~BOS~SYMBOL~": [1], "</s>": [2], "<pad>": [3], "mod": [4], "=": [5], " ": [6], "0": [7], "1": [8], "2": [9], "3": [10], "4": [11], "5": [12], "6": [13], "7": [14], "8": [15], "9": [16]}
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "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": 4,
+      "content": "mod",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 5,
+      "content": "=",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 6,
+      "content": " ",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Sequence",
+    "pretokenizers": [
+      {
+        "type": "Split",
+        "pattern": {
+          "Regex": "\\p{N}"
+        },
+        "behavior": "Isolated",
+        "invert": false
+      },
+      {
+        "type": "ByteLevel",
+        "add_prefix_space": false,
+        "trim_offsets": true,
+        "use_regex": false
+      }
+    ]
+  },
+  "post_processor": null,
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": "<unk>",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "<unk>": 0,
+      "<s>": 1,
+      "</s>": 2,
+      "<pad>": 3,
+      "mod": 4,
+      "=": 5,
+      " ": 6,
+      "0": 7,
+      "1": 8,
+      "2": 9,
+      "3": 10,
+      "4": 11,
+      "5": 12,
+      "6": 13,
+      "7": 14,
+      "8": 15,
+      "9": 16
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -1 +1,74 @@
-{"data": {"tokenizer": {"name": "huggingface", "path": "flexitok/mod-tokenizers-individual"}}}
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "mod",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "=",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": " ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "mod",
+    "=",
+    " "
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>",
+  "number_handling": "individual"
+}

vocab.json

@@ -1,19 +1,19 @@
 {
+  "=": 5,
+  "2": 9,
+  "</s>": 2,
   "<unk>": 0,
-  "mod": 4,
   "4": 11,
-  "=": 5,
   "1": 8,
   "<pad>": 3,
-  "7": 14,
-  "5": 12,
   "3": 10,
-  "9": 16,
+  " ": 6,
+  "mod": 4,
   "<s>": 1,
-  "2": 9,
-  "0": 7,
-  "8": 15,
+  "9": 16,
+  "5": 12,
+  "7": 14,
   "6": 13,
-  " ": 6,
-  "</s>": 2
+  "8": 15,
+  "0": 7
 }