Upload tokenizer
Browse files- special_tokens_map.json +2 -0
- tokenizer_config.json +18 -0
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"mask_token": "*",
|
| 3 |
"pad_token": "-",
|
| 4 |
"sep_token": "|",
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<",
|
| 3 |
+
"eos_token": ">",
|
| 4 |
"mask_token": "*",
|
| 5 |
"pad_token": "-",
|
| 6 |
"sep_token": "|",
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"21": {
|
| 4 |
"content": "-",
|
| 5 |
"lstrip": false,
|
|
@@ -8,6 +16,14 @@
|
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
"23": {
|
| 12 |
"content": "*",
|
| 13 |
"lstrip": false,
|
|
@@ -33,7 +49,9 @@
|
|
| 33 |
"special": true
|
| 34 |
}
|
| 35 |
},
|
|
|
|
| 36 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 37 |
"mask_token": "*",
|
| 38 |
"model_max_length": 1000000000000000019884624838656,
|
| 39 |
"pad_token": "-",
|
|
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
"21": {
|
| 12 |
"content": "-",
|
| 13 |
"lstrip": false,
|
|
|
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
+
"22": {
|
| 20 |
+
"content": ">",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
"23": {
|
| 28 |
"content": "*",
|
| 29 |
"lstrip": false,
|
|
|
|
| 49 |
"special": true
|
| 50 |
}
|
| 51 |
},
|
| 52 |
+
"bos_token": "<",
|
| 53 |
"clean_up_tokenization_spaces": false,
|
| 54 |
+
"eos_token": ">",
|
| 55 |
"mask_token": "*",
|
| 56 |
"model_max_length": 1000000000000000019884624838656,
|
| 57 |
"pad_token": "-",
|