Upload tokenizer
Browse files- special_tokens_map.json +4 -4
- tokenizer.json +12 -12
- tokenizer_config.json +12 -10
special_tokens_map.json
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"cls_token": {
|
| 10 |
-
"content": "<
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
|
@@ -21,21 +21,21 @@
|
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
"mask_token": {
|
| 24 |
-
"content": "<MASK>",
|
| 25 |
"lstrip": false,
|
| 26 |
"normalized": false,
|
| 27 |
"rstrip": false,
|
| 28 |
"single_word": false
|
| 29 |
},
|
| 30 |
"pad_token": {
|
| 31 |
-
"content": "<PAD>",
|
| 32 |
"lstrip": false,
|
| 33 |
"normalized": false,
|
| 34 |
"rstrip": false,
|
| 35 |
"single_word": false
|
| 36 |
},
|
| 37 |
"sep_token": {
|
| 38 |
-
"content": "
|
| 39 |
"lstrip": false,
|
| 40 |
"normalized": false,
|
| 41 |
"rstrip": false,
|
|
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"cls_token": {
|
| 10 |
+
"content": "<CLS|LLM-jp>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
|
|
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
"mask_token": {
|
| 24 |
+
"content": "<MASK|LLM-jp>",
|
| 25 |
"lstrip": false,
|
| 26 |
"normalized": false,
|
| 27 |
"rstrip": false,
|
| 28 |
"single_word": false
|
| 29 |
},
|
| 30 |
"pad_token": {
|
| 31 |
+
"content": "<PAD|LLM-jp>",
|
| 32 |
"lstrip": false,
|
| 33 |
"normalized": false,
|
| 34 |
"rstrip": false,
|
| 35 |
"single_word": false
|
| 36 |
},
|
| 37 |
"sep_token": {
|
| 38 |
+
"content": "<SEP|LLM-jp>",
|
| 39 |
"lstrip": false,
|
| 40 |
"normalized": false,
|
| 41 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
@@ -32,7 +32,7 @@
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 3,
|
| 35 |
-
"content": "<MASK>",
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
|
@@ -41,7 +41,7 @@
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 4,
|
| 44 |
-
"content": "<PAD>",
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
|
@@ -50,7 +50,7 @@
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 5,
|
| 53 |
-
"content": "<CLS>",
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
|
@@ -59,7 +59,7 @@
|
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 6,
|
| 62 |
-
"content": "<SEP>",
|
| 63 |
"single_word": false,
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
|
@@ -68,7 +68,7 @@
|
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 7,
|
| 71 |
-
"content": "<EOD>",
|
| 72 |
"single_word": false,
|
| 73 |
"lstrip": false,
|
| 74 |
"rstrip": false,
|
|
@@ -145,8 +145,8 @@
|
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"SpecialToken": {
|
| 148 |
-
"id": "
|
| 149 |
-
"type_id":
|
| 150 |
}
|
| 151 |
}
|
| 152 |
],
|
|
@@ -213,23 +213,23 @@
|
|
| 213 |
-127.5
|
| 214 |
],
|
| 215 |
[
|
| 216 |
-
"<MASK>",
|
| 217 |
-127.5
|
| 218 |
],
|
| 219 |
[
|
| 220 |
-
"<PAD>",
|
| 221 |
-127.5
|
| 222 |
],
|
| 223 |
[
|
| 224 |
-
"<CLS>",
|
| 225 |
-127.5
|
| 226 |
],
|
| 227 |
[
|
| 228 |
-
"<SEP>",
|
| 229 |
-127.5
|
| 230 |
],
|
| 231 |
[
|
| 232 |
-
"<EOD>",
|
| 233 |
-127.5
|
| 234 |
],
|
| 235 |
[
|
|
|
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 3,
|
| 35 |
+
"content": "<MASK|LLM-jp>",
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
|
|
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 4,
|
| 44 |
+
"content": "<PAD|LLM-jp>",
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
|
|
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"id": 5,
|
| 53 |
+
"content": "<CLS|LLM-jp>",
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
|
|
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"id": 6,
|
| 62 |
+
"content": "<SEP|LLM-jp>",
|
| 63 |
"single_word": false,
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
|
|
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"id": 7,
|
| 71 |
+
"content": "<EOD|LLM-jp>",
|
| 72 |
"single_word": false,
|
| 73 |
"lstrip": false,
|
| 74 |
"rstrip": false,
|
|
|
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"SpecialToken": {
|
| 148 |
+
"id": "</s>",
|
| 149 |
+
"type_id": 0
|
| 150 |
}
|
| 151 |
}
|
| 152 |
],
|
|
|
|
| 213 |
-127.5
|
| 214 |
],
|
| 215 |
[
|
| 216 |
+
"<MASK|LLM-jp>",
|
| 217 |
-127.5
|
| 218 |
],
|
| 219 |
[
|
| 220 |
+
"<PAD|LLM-jp>",
|
| 221 |
-127.5
|
| 222 |
],
|
| 223 |
[
|
| 224 |
+
"<CLS|LLM-jp>",
|
| 225 |
-127.5
|
| 226 |
],
|
| 227 |
[
|
| 228 |
+
"<SEP|LLM-jp>",
|
| 229 |
-127.5
|
| 230 |
],
|
| 231 |
[
|
| 232 |
+
"<EOD|LLM-jp>",
|
| 233 |
-127.5
|
| 234 |
],
|
| 235 |
[
|
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<unk>",
|
|
@@ -25,7 +27,7 @@
|
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
"3": {
|
| 28 |
-
"content": "<MASK>",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": false,
|
|
@@ -33,7 +35,7 @@
|
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
"4": {
|
| 36 |
-
"content": "<PAD>",
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
| 39 |
"rstrip": false,
|
|
@@ -41,7 +43,7 @@
|
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
"5": {
|
| 44 |
-
"content": "<CLS>",
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
| 47 |
"rstrip": false,
|
|
@@ -49,7 +51,7 @@
|
|
| 49 |
"special": true
|
| 50 |
},
|
| 51 |
"6": {
|
| 52 |
-
"content": "<SEP>",
|
| 53 |
"lstrip": false,
|
| 54 |
"normalized": false,
|
| 55 |
"rstrip": false,
|
|
@@ -57,7 +59,7 @@
|
|
| 57 |
"special": true
|
| 58 |
},
|
| 59 |
"7": {
|
| 60 |
-
"content": "<EOD>",
|
| 61 |
"lstrip": false,
|
| 62 |
"normalized": false,
|
| 63 |
"rstrip": false,
|
|
@@ -67,14 +69,14 @@
|
|
| 67 |
},
|
| 68 |
"bos_token": "<s>",
|
| 69 |
"clean_up_tokenization_spaces": false,
|
| 70 |
-
"cls_token": "<
|
| 71 |
-
"eod_token": "
|
| 72 |
"eos_token": "</s>",
|
| 73 |
"extra_ids": 0,
|
| 74 |
-
"mask_token": "<MASK>",
|
| 75 |
"model_max_length": 1000000000000000019884624838656,
|
| 76 |
-
"pad_token": "<PAD>",
|
| 77 |
-
"sep_token": "
|
| 78 |
"sp_model_kwargs": {},
|
| 79 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 80 |
"unk_token": "<unk>"
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
|
|
| 27 |
"special": true
|
| 28 |
},
|
| 29 |
"3": {
|
| 30 |
+
"content": "<MASK|LLM-jp>",
|
| 31 |
"lstrip": false,
|
| 32 |
"normalized": false,
|
| 33 |
"rstrip": false,
|
|
|
|
| 35 |
"special": true
|
| 36 |
},
|
| 37 |
"4": {
|
| 38 |
+
"content": "<PAD|LLM-jp>",
|
| 39 |
"lstrip": false,
|
| 40 |
"normalized": false,
|
| 41 |
"rstrip": false,
|
|
|
|
| 43 |
"special": true
|
| 44 |
},
|
| 45 |
"5": {
|
| 46 |
+
"content": "<CLS|LLM-jp>",
|
| 47 |
"lstrip": false,
|
| 48 |
"normalized": false,
|
| 49 |
"rstrip": false,
|
|
|
|
| 51 |
"special": true
|
| 52 |
},
|
| 53 |
"6": {
|
| 54 |
+
"content": "<SEP|LLM-jp>",
|
| 55 |
"lstrip": false,
|
| 56 |
"normalized": false,
|
| 57 |
"rstrip": false,
|
|
|
|
| 59 |
"special": true
|
| 60 |
},
|
| 61 |
"7": {
|
| 62 |
+
"content": "<EOD|LLM-jp>",
|
| 63 |
"lstrip": false,
|
| 64 |
"normalized": false,
|
| 65 |
"rstrip": false,
|
|
|
|
| 69 |
},
|
| 70 |
"bos_token": "<s>",
|
| 71 |
"clean_up_tokenization_spaces": false,
|
| 72 |
+
"cls_token": "<CLS|LLM-jp>",
|
| 73 |
+
"eod_token": "</s>",
|
| 74 |
"eos_token": "</s>",
|
| 75 |
"extra_ids": 0,
|
| 76 |
+
"mask_token": "<MASK|LLM-jp>",
|
| 77 |
"model_max_length": 1000000000000000019884624838656,
|
| 78 |
+
"pad_token": "<PAD|LLM-jp>",
|
| 79 |
+
"sep_token": "<SEP|LLM-jp>",
|
| 80 |
"sp_model_kwargs": {},
|
| 81 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 82 |
"unk_token": "<unk>"
|