Upload folder using huggingface_hub

README.md

@@ -0,0 +1,44 @@
+---
+license: mit
+language:
+- und  # ISO 639-3 code or "und" if not identifiable
+tags:
+- tokenizer
+- bpe
+- flexitok
+- fineweb2
+---
+
+# Byte-Level BPE Tokenizer: numeric (0K)
+
+A **Byte-Level BPE** tokenizer trained on **numeric** data from Fineweb-2-HQ.
+
+## Training Details
+
+| Parameter | Value |
+|-----------|-------|
+| Algorithm | Byte-Level BPE |
+| Language | `numeric` |
+| Target Vocab Size | 17 |
+| Final Vocab Size | 17 |
+| Pre-tokenizer | byte_level |
+| Number handling | individual |
+| Contraction handling | False |
+| Normalizer | NONE |
+| Special Tokens | `<s>`, `</s>`, `<pad>`, `<unk>` |
+| Training Shards | 1 |
+
+## Usage
+
+```python
+from transformers import AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("None")
+tokens = tokenizer.encode("Hello, world!")
+```
+
+## Files
+
+- `tokenizer.json` — Full HuggingFace tokenizer
+- `vocab.json` — Vocabulary mapping
+- `merges.txt` — BPE merge rules

merges.txt

@@ -0,0 +1 @@
+#version: 0.2

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "mod",
+    "=",
+    " "
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,127 @@
+{
+  "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": true
+      }
+    ]
+  },
+  "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

@@ -0,0 +1,73 @@
+{
+  "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>"
+}

vocab.json

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