Upload folder using huggingface_hub

README.md

@@ -1,7 +1,7 @@
 ---
 license: mit
 language:
-- arb
+- arb  # ISO 639-3 code or "und" if not identifiable
 tags:
 - tokenizer
 - bpe
@@ -20,8 +20,10 @@ A **Byte-Level BPE** tokenizer trained on **arb_Arab** data from Fineweb-2-HQ.
 | Algorithm | Byte-Level BPE |
 | Language | `arb_Arab` |
 | Target Vocab Size | 16,000 |
-| Final Vocab Size | 0 |
-| Pre-tokenizer | ByteLevel |
+| Final Vocab Size | 16,000 |
+| Pre-tokenizer | gpt4 |
+| Number handling | individual |
+| Contraction handling | True |
 | Normalizer | NFC |
 | Special Tokens | `<s>`, `</s>`, `<pad>`, `<unk>` |
 | Training Shards | 2 |
@@ -40,3 +42,8 @@ tokens = tokenizer.encode("Hello, world!")
 - `tokenizer.json` — Full HuggingFace tokenizer
 - `vocab.json` — Vocabulary mapping
 - `merges.txt` — BPE merge rules
+
+## Sample Encoding
+| Text | Tokens | Token IDs |
+|------|--------|-----------|
+| `Hello, world! 12345 This is a test. こんにちは` | `H, ell, o, ,, Ġw, orld, !, Ġ, 12, 3, 45, ĠTh, is, Ġis, Ġa, Ġt, est, ., Ġ, ãģ` | `43, 4047, 82, 15, 1168, 9534, 4, 178, 1228, 22, 4101, 5756, 853, 3818, 1153, 605, 2611, 17, 178, 11047` |

tokenizer_config.json

@@ -40,5 +40,6 @@
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": "<unk>"
-}
+  "unk_token": "<unk>",
+  "number_handling": "individual"
+}