Upload folder using huggingface_hub
Browse files- added_tokens.json +41 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"AGN": 25000,
|
| 3 |
+
"ATA": 25002,
|
| 4 |
+
"ATG": 25011,
|
| 5 |
+
"ATN": 25034,
|
| 6 |
+
"CCG": 25016,
|
| 7 |
+
"CCN": 25006,
|
| 8 |
+
"CGN": 25021,
|
| 9 |
+
"CTA": 25003,
|
| 10 |
+
"CTG": 25008,
|
| 11 |
+
"CTN": 25022,
|
| 12 |
+
"GAN": 25027,
|
| 13 |
+
"GCG": 25032,
|
| 14 |
+
"GCN": 25014,
|
| 15 |
+
"GGN": 25017,
|
| 16 |
+
"GTA": 25030,
|
| 17 |
+
"GTG": 25033,
|
| 18 |
+
"GTN": 25029,
|
| 19 |
+
"NAA": 25023,
|
| 20 |
+
"NAC": 25010,
|
| 21 |
+
"NAG": 25019,
|
| 22 |
+
"NAT": 25025,
|
| 23 |
+
"NCA": 25020,
|
| 24 |
+
"NCG": 25005,
|
| 25 |
+
"NCT": 25035,
|
| 26 |
+
"NGA": 25009,
|
| 27 |
+
"NGC": 25024,
|
| 28 |
+
"NGG": 25026,
|
| 29 |
+
"NGT": 25036,
|
| 30 |
+
"NTA": 25028,
|
| 31 |
+
"NTC": 25012,
|
| 32 |
+
"NTG": 25004,
|
| 33 |
+
"NTT": 25018,
|
| 34 |
+
"TAN": 25013,
|
| 35 |
+
"TCG": 25015,
|
| 36 |
+
"TCN": 25031,
|
| 37 |
+
"TGN": 25038,
|
| 38 |
+
"TTA": 25001,
|
| 39 |
+
"TTG": 25037,
|
| 40 |
+
"TTN": 25007
|
| 41 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_lower_case": false,
|
| 4 |
+
"mask_token": "[MASK]",
|
| 5 |
+
"model_max_length": 512,
|
| 6 |
+
"name_or_path": "/mnt/volume/project/5mC/pretrainedModel/distilbert/tokenizer/distilbert_seq_tax_trained",
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"special_tokens_map_file": null,
|
| 10 |
+
"strip_accents": null,
|
| 11 |
+
"tokenize_chinese_chars": true,
|
| 12 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 13 |
+
"unk_token": "[UNK]"
|
| 14 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|