Upload tokenizer
#1
by
Cratee
- opened
- merges.txt +1 -1
- tokenizer.json +2 -6
- tokenizer_config.json +1 -2
merges.txt
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
#version: 0.2
|
| 2 |
Ġ t
|
| 3 |
Ġ a
|
| 4 |
h e
|
|
|
|
| 1 |
+
#version: 0.2
|
| 2 |
Ġ t
|
| 3 |
Ġ a
|
| 4 |
h e
|
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 512,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
@@ -87,6 +82,7 @@
|
|
| 87 |
"continuing_subword_prefix": "",
|
| 88 |
"end_of_word_suffix": "",
|
| 89 |
"fuse_unk": false,
|
|
|
|
| 90 |
"vocab": {
|
| 91 |
"<s>": 0,
|
| 92 |
"<pad>": 1,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
|
|
|
| 82 |
"continuing_subword_prefix": "",
|
| 83 |
"end_of_word_suffix": "",
|
| 84 |
"fuse_unk": false,
|
| 85 |
+
"byte_fallback": false,
|
| 86 |
"vocab": {
|
| 87 |
"<s>": 0,
|
| 88 |
"<pad>": 1,
|
tokenizer_config.json
CHANGED
|
@@ -1,15 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"bos_token": "<s>",
|
|
|
|
| 4 |
"cls_token": "<s>",
|
| 5 |
"eos_token": "</s>",
|
| 6 |
"errors": "replace",
|
| 7 |
"mask_token": "<mask>",
|
| 8 |
"model_max_length": 1024,
|
| 9 |
-
"name_or_path": "facebook/bart-large",
|
| 10 |
"pad_token": "<pad>",
|
| 11 |
"sep_token": "</s>",
|
| 12 |
-
"special_tokens_map_file": null,
|
| 13 |
"tokenizer_class": "BartTokenizer",
|
| 14 |
"trim_offsets": true,
|
| 15 |
"unk_token": "<unk>"
|
|
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
"cls_token": "<s>",
|
| 6 |
"eos_token": "</s>",
|
| 7 |
"errors": "replace",
|
| 8 |
"mask_token": "<mask>",
|
| 9 |
"model_max_length": 1024,
|
|
|
|
| 10 |
"pad_token": "<pad>",
|
| 11 |
"sep_token": "</s>",
|
|
|
|
| 12 |
"tokenizer_class": "BartTokenizer",
|
| 13 |
"trim_offsets": true,
|
| 14 |
"unk_token": "<unk>"
|