Upload tokenizer
Browse files- special_tokens_map.json +25 -3
- tokenizer_config.json +7 -1
special_tokens_map.json
CHANGED
|
@@ -11,9 +11,31 @@
|
|
| 11 |
"▁<PRE>",
|
| 12 |
"▁<MID>",
|
| 13 |
"▁<SUF>",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
"▁<EOT>"
|
| 15 |
],
|
| 16 |
-
"bos_token":
|
| 17 |
-
|
| 18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
}
|
|
|
|
| 11 |
"▁<PRE>",
|
| 12 |
"▁<MID>",
|
| 13 |
"▁<SUF>",
|
| 14 |
+
"▁<EOT>",
|
| 15 |
+
"▁<PRE>",
|
| 16 |
+
"▁<MID>",
|
| 17 |
+
"▁<SUF>",
|
| 18 |
"▁<EOT>"
|
| 19 |
],
|
| 20 |
+
"bos_token": {
|
| 21 |
+
"content": "<s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"eos_token": {
|
| 28 |
+
"content": "</s>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
},
|
| 34 |
+
"unk_token": {
|
| 35 |
+
"content": "<unk>",
|
| 36 |
+
"lstrip": false,
|
| 37 |
+
"normalized": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"single_word": false
|
| 40 |
+
}
|
| 41 |
}
|
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<unk>",
|
|
@@ -69,6 +71,10 @@
|
|
| 69 |
"▁<PRE>",
|
| 70 |
"▁<MID>",
|
| 71 |
"▁<SUF>",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
"▁<EOT>"
|
| 73 |
],
|
| 74 |
"bos_token": "<s>",
|
|
@@ -76,7 +82,7 @@
|
|
| 76 |
"eos_token": "</s>",
|
| 77 |
"eot_token": "▁<EOT>",
|
| 78 |
"fill_token": "<FILL_ME>",
|
| 79 |
-
"legacy":
|
| 80 |
"middle_token": "▁<MID>",
|
| 81 |
"model_max_length": 1000000000000000019884624838656,
|
| 82 |
"pad_token": null,
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
|
|
| 71 |
"▁<PRE>",
|
| 72 |
"▁<MID>",
|
| 73 |
"▁<SUF>",
|
| 74 |
+
"▁<EOT>",
|
| 75 |
+
"▁<PRE>",
|
| 76 |
+
"▁<MID>",
|
| 77 |
+
"▁<SUF>",
|
| 78 |
"▁<EOT>"
|
| 79 |
],
|
| 80 |
"bos_token": "<s>",
|
|
|
|
| 82 |
"eos_token": "</s>",
|
| 83 |
"eot_token": "▁<EOT>",
|
| 84 |
"fill_token": "<FILL_ME>",
|
| 85 |
+
"legacy": false,
|
| 86 |
"middle_token": "▁<MID>",
|
| 87 |
"model_max_length": 1000000000000000019884624838656,
|
| 88 |
"pad_token": null,
|