Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"pad_token": "[PAD]",
|
| 6 |
+
"sep_token": "[SEP]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_special_token": true,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"lowercase": true,
|
| 7 |
+
"name_or_path": "poetry-model",
|
| 8 |
+
"pad_token": "[PAD]",
|
| 9 |
+
"padding_side": "left",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"special_tokens_map_file": "poetry-model/special_tokens_map.json",
|
| 12 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 13 |
+
}
|