Commit
•
a8a668a
1
Parent(s):
4fca215
Upload tokenizer
Browse files- merges.txt +0 -0
- special_tokens_map.json +1 -1
- tokenizer.json +2 -2
- tokenizer_config.json +16 -11
- vocab.json +0 -0
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
"mask_token": {
|
| 6 |
"content": "<mask>",
|
| 7 |
"lstrip": true,
|
| 8 |
-
"normalized":
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
|
|
| 5 |
"mask_token": {
|
| 6 |
"content": "<mask>",
|
| 7 |
"lstrip": true,
|
| 8 |
+
"normalized": true,
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
tokenizer.json
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:804dadca9c4bc7c26a59a2837cac751b3eff43193367765b28c6d61aa299fa1c
|
| 3 |
+
size 2230006
|
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,8 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
-
"content": "<
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
|
@@ -9,7 +10,7 @@
|
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
"1": {
|
| 12 |
-
"content": "<
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": false,
|
|
@@ -17,24 +18,24 @@
|
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
"2": {
|
| 20 |
-
"content": "
|
| 21 |
-
"lstrip":
|
| 22 |
-
"normalized":
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
"3": {
|
| 28 |
-
"content": "<
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": false,
|
| 32 |
"single_word": false,
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
-
"
|
| 36 |
-
"content": "
|
| 37 |
-
"lstrip":
|
| 38 |
"normalized": false,
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
|
@@ -45,10 +46,14 @@
|
|
| 45 |
"clean_up_tokenization_spaces": true,
|
| 46 |
"cls_token": "<s>",
|
| 47 |
"eos_token": "</s>",
|
|
|
|
|
|
|
| 48 |
"mask_token": "<mask>",
|
| 49 |
-
"
|
|
|
|
| 50 |
"pad_token": "<pad>",
|
| 51 |
"sep_token": "</s>",
|
| 52 |
-
"tokenizer_class": "
|
|
|
|
| 53 |
"unk_token": "<unk>"
|
| 54 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
"lstrip": false,
|
| 7 |
"normalized": false,
|
| 8 |
"rstrip": false,
|
|
|
|
| 10 |
"special": true
|
| 11 |
},
|
| 12 |
"1": {
|
| 13 |
+
"content": "<unk>",
|
| 14 |
"lstrip": false,
|
| 15 |
"normalized": false,
|
| 16 |
"rstrip": false,
|
|
|
|
| 18 |
"special": true
|
| 19 |
},
|
| 20 |
"2": {
|
| 21 |
+
"content": "<mask>",
|
| 22 |
+
"lstrip": true,
|
| 23 |
+
"normalized": true,
|
| 24 |
"rstrip": false,
|
| 25 |
"single_word": false,
|
| 26 |
"special": true
|
| 27 |
},
|
| 28 |
"3": {
|
| 29 |
+
"content": "<s>",
|
| 30 |
"lstrip": false,
|
| 31 |
"normalized": false,
|
| 32 |
"rstrip": false,
|
| 33 |
"single_word": false,
|
| 34 |
"special": true
|
| 35 |
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "</s>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
"normalized": false,
|
| 40 |
"rstrip": false,
|
| 41 |
"single_word": false,
|
|
|
|
| 46 |
"clean_up_tokenization_spaces": true,
|
| 47 |
"cls_token": "<s>",
|
| 48 |
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"keep_accents": true,
|
| 51 |
"mask_token": "<mask>",
|
| 52 |
+
"max_len": 50,
|
| 53 |
+
"model_max_length": 50,
|
| 54 |
"pad_token": "<pad>",
|
| 55 |
"sep_token": "</s>",
|
| 56 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 57 |
+
"trim_offsets": true,
|
| 58 |
"unk_token": "<unk>"
|
| 59 |
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|