Upload tokenizer
Browse files- special_tokens_map.json +0 -9
- tokenizer.json +0 -9
- tokenizer_config.json +0 -11
special_tokens_map.json
CHANGED
|
@@ -1,13 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
{
|
| 4 |
-
"content": "<|EOT|>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false
|
| 9 |
-
}
|
| 10 |
-
],
|
| 11 |
"bos_token": {
|
| 12 |
"content": "<|endoftext|>",
|
| 13 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": {
|
| 3 |
"content": "<|endoftext|>",
|
| 4 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
@@ -200,15 +200,6 @@
|
|
| 200 |
"rstrip": false,
|
| 201 |
"normalized": false,
|
| 202 |
"special": true
|
| 203 |
-
},
|
| 204 |
-
{
|
| 205 |
-
"id": 100278,
|
| 206 |
-
"content": "<|EOT|>",
|
| 207 |
-
"single_word": false,
|
| 208 |
-
"lstrip": false,
|
| 209 |
-
"rstrip": false,
|
| 210 |
-
"normalized": false,
|
| 211 |
-
"special": true
|
| 212 |
}
|
| 213 |
],
|
| 214 |
"normalizer": null,
|
|
|
|
| 200 |
"rstrip": false,
|
| 201 |
"normalized": false,
|
| 202 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 203 |
}
|
| 204 |
],
|
| 205 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
|
@@ -176,19 +176,8 @@
|
|
| 176 |
"rstrip": false,
|
| 177 |
"single_word": false,
|
| 178 |
"special": true
|
| 179 |
-
},
|
| 180 |
-
"100278": {
|
| 181 |
-
"content": "<|EOT|>",
|
| 182 |
-
"lstrip": false,
|
| 183 |
-
"normalized": false,
|
| 184 |
-
"rstrip": false,
|
| 185 |
-
"single_word": false,
|
| 186 |
-
"special": true
|
| 187 |
}
|
| 188 |
},
|
| 189 |
-
"additional_special_tokens": [
|
| 190 |
-
"<|EOT|>"
|
| 191 |
-
],
|
| 192 |
"bos_token": "<|endoftext|>",
|
| 193 |
"clean_up_tokenization_spaces": false,
|
| 194 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 176 |
"rstrip": false,
|
| 177 |
"single_word": false,
|
| 178 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 179 |
}
|
| 180 |
},
|
|
|
|
|
|
|
|
|
|
| 181 |
"bos_token": "<|endoftext|>",
|
| 182 |
"clean_up_tokenization_spaces": false,
|
| 183 |
"eos_token": "<|endoftext|>",
|