Upload folder using huggingface_hub
Browse files- sentencepiece.model +3 -0
- sentencepiece.vocab +0 -0
- spiece.model +3 -0
- tokenizer_config.json +16 -0
sentencepiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04fe95939f9a5276c465863b675b38359a52499bbbbbd3c9b5a66513dcf9e085
|
| 3 |
+
size 911548
|
sentencepiece.vocab
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04fe95939f9a5276c465863b675b38359a52499bbbbbd3c9b5a66513dcf9e085
|
| 3 |
+
size 911548
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"cls_token": "[CLS]",
|
| 6 |
+
"do_lower_case": true,
|
| 7 |
+
"eos_token": "</s>",
|
| 8 |
+
"keep_accents": false,
|
| 9 |
+
"mask_token": "[MASK]",
|
| 10 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 11 |
+
"pad_token": "<pad>",
|
| 12 |
+
"sep_token": "[SEP]",
|
| 13 |
+
"tokenizer_class": "AlbertTokenizer",
|
| 14 |
+
"trim_offsets": true,
|
| 15 |
+
"unk_token": "<unk>"
|
| 16 |
+
}
|