Upload folder using huggingface_hub

README.md

@@ -20,19 +20,18 @@ A **Byte-Level BPE** tokenizer trained on **fas_Arab** data from Fineweb-2-HQ.
 | Algorithm | Byte-Level BPE |
 | Language | `fas_Arab` |
 | Target Vocab Size | 32,000 |
-| Final Vocab Size | 0 |
+| Final Vocab Size | 32,000 |
 | Pre-tokenizer | ByteLevel |
 | Normalizer | NFC |
 | Special Tokens | `<s>`, `</s>`, `<pad>`, `<unk>` |
 | Training Shards | 2 |
-| Data Source | `/scratch/gsa/data/flexitok//fas_Arab/` |
 
 ## Usage
 
 ```python
 from transformers import AutoTokenizer
 
-tokenizer = AutoTokenizer.from_pretrained("<repo_id>")
+tokenizer = AutoTokenizer.from_pretrained("flexitok/-bpe_fas_Arab_32000")
 tokens = tokenizer.encode("Hello, world!")
 ```
 

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 +1,44 @@
+{
+  "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>"
+}