Commit
·
05b5076
1
Parent(s):
a91a280
Upload tokenizer
Browse files- added_tokens.json +6 -0
- merges.txt +0 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</[SEQ]>": 50258,
|
| 3 |
+
"<[PAD]>": 50259,
|
| 4 |
+
"<[SEQ]>": 50257,
|
| 5 |
+
"<[UNK]>": 50260
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<[SEQ]>",
|
| 3 |
+
"eos_token": "</[SEQ]>",
|
| 4 |
+
"pad_token": "<[PAD]>",
|
| 5 |
+
"unk_token": "<[UNK]>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|endoftext|>",
|
| 6 |
+
"model_max_length": 256,
|
| 7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 8 |
+
"unk_token": "<|endoftext|>"
|
| 9 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|