Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer_config.json +19 -0
- vocab.txt +0 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"mask_token": "<mask>",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_map": {
|
3 |
+
"AutoTokenizer": [
|
4 |
+
"openbmb/cpm-bee-10b--tokenization_cpmbee.CpmBeeTokenizer",
|
5 |
+
null
|
6 |
+
]
|
7 |
+
},
|
8 |
+
"bos_token": "<s>",
|
9 |
+
"clean_up_tokenization_spaces": true,
|
10 |
+
"eos_token": "</s>",
|
11 |
+
"line_token": "\n",
|
12 |
+
"mask_token": "<mask>",
|
13 |
+
"model_max_length": 4096,
|
14 |
+
"pad_token": "<pad>",
|
15 |
+
"padding_side": "left",
|
16 |
+
"space_token": " ",
|
17 |
+
"tokenizer_class": "CpmBeeTokenizer",
|
18 |
+
"unk_token": "<unk>"
|
19 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|