Delete hist_ga_fast_sentencepiece
Browse files
hist_ga_fast_sentencepiece/special_tokens_map.json
DELETED
|
@@ -1,9 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": "<s>",
|
| 3 |
-
"cls_token": "<s>",
|
| 4 |
-
"eos_token": "</s>",
|
| 5 |
-
"mask_token": "<mask>",
|
| 6 |
-
"pad_token": "<pad>",
|
| 7 |
-
"sep_token": "</s>",
|
| 8 |
-
"unk_token": "<unk>"
|
| 9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
hist_ga_fast_sentencepiece/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
hist_ga_fast_sentencepiece/tokenizer_config.json
DELETED
|
@@ -1,14 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"clean_up_tokenization_spaces": true,
|
| 3 |
-
"model_max_length": 64,
|
| 4 |
-
"special_tokens": [
|
| 5 |
-
"<s>",
|
| 6 |
-
"<pad>",
|
| 7 |
-
"</s>",
|
| 8 |
-
"<unk>",
|
| 9 |
-
"<mask>",
|
| 10 |
-
"<true>",
|
| 11 |
-
"<false>"
|
| 12 |
-
],
|
| 13 |
-
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 14 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|