Upload tokenizer
Browse files- README.md +1 -1
- special_tokens_map.json +42 -6
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: duraad/nep-spell-mbart
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: nep-spell-mbart
|
| 7 |
results: []
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
+
base_model: duraad/nep-spell-mbart
|
| 5 |
model-index:
|
| 6 |
- name: nep-spell-mbart
|
| 7 |
results: []
|
special_tokens_map.json
CHANGED
|
@@ -26,9 +26,27 @@
|
|
| 26 |
"vi_VN",
|
| 27 |
"zh_CN"
|
| 28 |
],
|
| 29 |
-
"bos_token":
|
| 30 |
-
|
| 31 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"mask_token": {
|
| 33 |
"content": "<mask>",
|
| 34 |
"lstrip": true,
|
|
@@ -36,7 +54,25 @@
|
|
| 36 |
"rstrip": false,
|
| 37 |
"single_word": false
|
| 38 |
},
|
| 39 |
-
"pad_token":
|
| 40 |
-
|
| 41 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
}
|
|
|
|
| 26 |
"vi_VN",
|
| 27 |
"zh_CN"
|
| 28 |
],
|
| 29 |
+
"bos_token": {
|
| 30 |
+
"content": "<s>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
},
|
| 36 |
+
"cls_token": {
|
| 37 |
+
"content": "<s>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false
|
| 42 |
+
},
|
| 43 |
+
"eos_token": {
|
| 44 |
+
"content": "</s>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false
|
| 49 |
+
},
|
| 50 |
"mask_token": {
|
| 51 |
"content": "<mask>",
|
| 52 |
"lstrip": true,
|
|
|
|
| 54 |
"rstrip": false,
|
| 55 |
"single_word": false
|
| 56 |
},
|
| 57 |
+
"pad_token": {
|
| 58 |
+
"content": "<pad>",
|
| 59 |
+
"lstrip": false,
|
| 60 |
+
"normalized": false,
|
| 61 |
+
"rstrip": false,
|
| 62 |
+
"single_word": false
|
| 63 |
+
},
|
| 64 |
+
"sep_token": {
|
| 65 |
+
"content": "</s>",
|
| 66 |
+
"lstrip": false,
|
| 67 |
+
"normalized": false,
|
| 68 |
+
"rstrip": false,
|
| 69 |
+
"single_word": false
|
| 70 |
+
},
|
| 71 |
+
"unk_token": {
|
| 72 |
+
"content": "<unk>",
|
| 73 |
+
"lstrip": false,
|
| 74 |
+
"normalized": false,
|
| 75 |
+
"rstrip": false,
|
| 76 |
+
"single_word": false
|
| 77 |
+
}
|
| 78 |
}
|