Upload folder using huggingface_hub
Browse files- tokenizer_config.json +20 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"unk_token": {
|
| 3 |
+
"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "__type": "AddedToken"
|
| 4 |
+
},
|
| 5 |
+
"model_max_length": 2048,
|
| 6 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 7 |
+
"auto_map": {
|
| 8 |
+
"AutoTokenizer": [
|
| 9 |
+
"tokenizers.Tokenizer",
|
| 10 |
+
null
|
| 11 |
+
]
|
| 12 |
+
},
|
| 13 |
+
"model_type": "unigram",
|
| 14 |
+
"vocab_size": 35590,
|
| 15 |
+
"language": ["th", "thai"],
|
| 16 |
+
"license": "apache-2.0",
|
| 17 |
+
"library_name": "tokenizers",
|
| 18 |
+
"tags": ["thai", "tokenizer", "nlp", "subword"],
|
| 19 |
+
"creation_date": "2025-07-02"
|
| 20 |
+
}
|