Upload 4 files
Browse files- processor_config.json +18 -0
- special_tokens_map.json +51 -0
- tokenizer_config.json +29 -0
- vocab.json +0 -0
processor_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"processor_class": "MorPieceProcessor",
|
| 3 |
+
"auto_map": {
|
| 4 |
+
"AutoProcessor": "morpiece_processor.MorPieceProcessor"
|
| 5 |
+
},
|
| 6 |
+
"tokenizer_class": "MorPieceTokenizer",
|
| 7 |
+
"feature_extractor_class": null,
|
| 8 |
+
"image_processor_class": null,
|
| 9 |
+
"audio_processor_class": null,
|
| 10 |
+
"morpiece_config": {
|
| 11 |
+
"vocab_size": 29066,
|
| 12 |
+
"min_frequency": 10,
|
| 13 |
+
"cutoff": 100,
|
| 14 |
+
"bf": 10,
|
| 15 |
+
"use_tokenizers_lib": true,
|
| 16 |
+
"processor_type": "text_only"
|
| 17 |
+
}
|
| 18 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"content": "<pad>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"mask_token": {
|
| 31 |
+
"content": "<mask>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "<sep>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"cls_token": {
|
| 45 |
+
"content": "<cls>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tokenizer_class": "MorPieceTokenizer",
|
| 3 |
+
"auto_map": {
|
| 4 |
+
"AutoTokenizer": [
|
| 5 |
+
"morpiece_tokenizer.MorPieceTokenizer",
|
| 6 |
+
null
|
| 7 |
+
]
|
| 8 |
+
},
|
| 9 |
+
"bos_token": "<s>",
|
| 10 |
+
"eos_token": "</s>",
|
| 11 |
+
"unk_token": "<unk>",
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"mask_token": "<mask>",
|
| 14 |
+
"sep_token": "<sep>",
|
| 15 |
+
"cls_token": "<cls>",
|
| 16 |
+
"model_max_length": 512,
|
| 17 |
+
"padding_side": "left",
|
| 18 |
+
"truncation_side": "right",
|
| 19 |
+
"chat_template": null,
|
| 20 |
+
"clean_up_tokenization_spaces": false,
|
| 21 |
+
"split_special_tokens": false,
|
| 22 |
+
"strip_accents": null,
|
| 23 |
+
"add_prefix_space": true,
|
| 24 |
+
"vocab_size": 29066,
|
| 25 |
+
"min_frequency": 10,
|
| 26 |
+
"cutoff": 100,
|
| 27 |
+
"bf": 10,
|
| 28 |
+
"use_tokenizers_lib": true
|
| 29 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|