chore: use original tokenizer and tokenizer config
Browse files- special_tokens_map.json +30 -0
- tokenizer.json +9 -2
- tokenizer_config.json +0 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
CHANGED
|
@@ -1,7 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
-
"padding":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
@@ -7058,7 +7065,7 @@
|
|
| 7058 |
"model": {
|
| 7059 |
"type": "BPE",
|
| 7060 |
"dropout": null,
|
| 7061 |
-
"unk_token":
|
| 7062 |
"continuing_subword_prefix": null,
|
| 7063 |
"end_of_word_suffix": null,
|
| 7064 |
"fuse_unk": true,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": null,
|
| 4 |
+
"padding": {
|
| 5 |
+
"strategy": "BatchLongest",
|
| 6 |
+
"direction": "Left",
|
| 7 |
+
"pad_to_multiple_of": null,
|
| 8 |
+
"pad_id": 2,
|
| 9 |
+
"pad_type_id": 0,
|
| 10 |
+
"pad_token": "</s>"
|
| 11 |
+
},
|
| 12 |
"added_tokens": [
|
| 13 |
{
|
| 14 |
"id": 0,
|
|
|
|
| 7065 |
"model": {
|
| 7066 |
"type": "BPE",
|
| 7067 |
"dropout": null,
|
| 7068 |
+
"unk_token": "<unk>",
|
| 7069 |
"continuing_subword_prefix": null,
|
| 7070 |
"end_of_word_suffix": null,
|
| 7071 |
"fuse_unk": true,
|
tokenizer_config.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|