Upload converted tokenizer

README.md

@@ -0,0 +1,25 @@
+---
+library_name: transformers
+tags:
+- tokenizer
+- sentencepiece
+---
+
+# SentencePiece-based Hugging Face tokenizer
+
+This repository contains a Hugging Face tokenizer converted from a SentencePiece model.
+
+## Load
+
+```python
+from transformers import AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("lanstat0123/multilingual_tokenizer")
+```
+
+## Special tokens
+
+```python
+print(tokenizer.special_tokens_map)
+print(len(tokenizer))
+```

tokenizer.json

@@ -0,0 +1,125 @@
+{
+  "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": "<|mdm_mask|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Metaspace",
+    "replacement": "▁",
+    "prepend_scheme": "first",
+    "split": false
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {}
+  },
+  "decoder": {
+    "type": "Sequence",
+    "decoders": [
+      {
+        "type": "Replace",
+        "pattern": {
+          "String": "▁"
+        },
+        "content": " "
+      },
+      {
+        "type": "ByteFallback"
+      },
+      {
+        "type": "Fuse"
+      },
+      {
+        "type": "Strip",
+        "content": " ",
+        "start": 1,
+        "stop": 0
+      }
+    ]
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": true,
+    "byte_fallback": true,
+    "ignore_merges": false,
+    "vocab": {
+      "<unk>": 0,
+      "<s>": 1,
+      "</s>": 2
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "mask_token": "<|mdm_mask|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}