add tokenizer
Browse files- special_tokens_map.json +9 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -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 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5cbdfa8aa7c54c8c5af85b78c309c54a5f2749a20468bf6f60eee007fe6fec1
|
| 3 |
+
size 805634
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [],
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "[CLS]",
|
| 5 |
+
"do_lower_case": true,
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"extra_ids": 0,
|
| 8 |
+
"mask_token": "[MASK]",
|
| 9 |
+
"name_or_path": "../input/image-captioning-v263/output/",
|
| 10 |
+
"pad_token": "[PAD]",
|
| 11 |
+
"sep_token": "[SEP]",
|
| 12 |
+
"sp_model_kwargs": {},
|
| 13 |
+
"special_tokens_map_file": "/root/.cache/huggingface/transformers/42091916a8a40b3949b8a4f56ce63e437a166ae0e88d1d15546860c13bdc5ceb.9049458ebcd1cf666b7b0a046aa394597f12e611077571cfc86e0938f8675d82",
|
| 14 |
+
"tokenizer_class": "T5Tokenizer",
|
| 15 |
+
"unk_token": "<unk>"
|
| 16 |
+
}
|