Commit
•
d24cd8e
1
Parent(s):
28a3550
Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +1 -6
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -13,7 +13,7 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token": "
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 2048,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
tokenizer_config.json
CHANGED
|
@@ -29,7 +29,7 @@
|
|
| 29 |
"clean_up_tokenization_spaces": false,
|
| 30 |
"eos_token": "</s>",
|
| 31 |
"legacy": false,
|
| 32 |
-
"model_max_length":
|
| 33 |
"pad_token": "<unk>",
|
| 34 |
"padding_side": "right",
|
| 35 |
"sp_model_kwargs": {},
|
|
|
|
| 29 |
"clean_up_tokenization_spaces": false,
|
| 30 |
"eos_token": "</s>",
|
| 31 |
"legacy": false,
|
| 32 |
+
"model_max_length": 4096,
|
| 33 |
"pad_token": "<unk>",
|
| 34 |
"padding_side": "right",
|
| 35 |
"sp_model_kwargs": {},
|