Commit
•
c27e877
1
Parent(s):
7726732
Upload tokenizer
Browse files- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<cls>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": "<mask>",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "<sep>",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
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 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<cls>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": "<mask>",
|
| 6 |
+
"model_max_length": 128,
|
| 7 |
+
"name_or_path": "/home/jonas/Documents/cmlscratch_backups/cramming/A6000amp_b4096_c5_o3_final/checkpoints/ScriptableMaskedLM_2022-12-21_2.0118",
|
| 8 |
+
"pad_token": "<pad>",
|
| 9 |
+
"sep_token": "<sep>",
|
| 10 |
+
"special_tokens_map_file": "/scratch1/jonas0/c4-subset_WordPiecex32768_e0501aeb87699de7500dc91a54939f44/tokenizer/special_tokens_map.json",
|
| 11 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 12 |
+
"unk_token": "<unk>"
|
| 13 |
+
}
|