feat: add tokenizer
Browse files- added_tokens.json +3 -0
- bpe.codes +0 -0
- special_tokens_map.json +9 -0
- tokenizer_config.json +12 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<mask>": 64000
|
| 3 |
+
}
|
bpe.codes
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"mask_token": "<mask>",
|
| 7 |
+
"model_max_length": 256,
|
| 8 |
+
"pad_token": "<pad>",
|
| 9 |
+
"sep_token": "</s>",
|
| 10 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 11 |
+
"unk_token": "<unk>"
|
| 12 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11cafebf9be52acb2504b6cfb5c414f0faf57c8f9b6c67b9a86b0a5ba25ba4d6
|
| 3 |
+
size 4344
|