Upload folder using huggingface_hub

README.md

@@ -1,7 +1,7 @@
 ---
 license: mit
 language:
-- ind
+- ind  # ISO 639-3 code or "und" if not identifiable
 tags:
 - tokenizer
 - bpe
@@ -20,8 +20,10 @@ A **Byte-Level BPE** tokenizer trained on **ind_Latn** data from Fineweb-2-HQ.
 | Algorithm | Byte-Level BPE |
 | Language | `ind_Latn` |
 | 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 |
@@ -31,7 +33,7 @@ A **Byte-Level BPE** tokenizer trained on **ind_Latn** data from Fineweb-2-HQ.
 ```python
 from transformers import AutoTokenizer
 
-tokenizer = AutoTokenizer.from_pretrained("<repo_id>")
+tokenizer = AutoTokenizer.from_pretrained("flexitok/-bpe_ind_Latn_16000")
 tokens = tokenizer.encode("Hello, world!")
 ```
 
@@ -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, ello, ,, Ġw, orld, !, Ġ, 12, 3, 45, ĠThis, Ġis, Ġa, Ġtest, ., Ġ, ãģ, ĵ, ãĤ, ĵ` | `43, 15028, 15, 383, 4635, 4, 177, 1430, 22, 4523, 14005, 1113, 349, 7050, 17, 177, 9778, 197, 15845, 197` |

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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
+    }
+  },
+  "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"
+}