Upload tokenizer
Browse files- special_tokens_map.json +14 -0
- tokenizer_config.json +2 -2
special_tokens_map.json
CHANGED
@@ -1,4 +1,18 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"pad_token": {
|
3 |
"content": "<|pad|>",
|
4 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
"pad_token": {
|
17 |
"content": "<|pad|>",
|
18 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -19,9 +19,9 @@
|
|
19 |
"special": true
|
20 |
}
|
21 |
},
|
22 |
-
"bos_token":
|
23 |
"clean_up_tokenization_spaces": true,
|
24 |
-
"eos_token":
|
25 |
"errors": "replace",
|
26 |
"model_max_length": 1024,
|
27 |
"pad_token": "<|pad|>",
|
|
|
19 |
"special": true
|
20 |
}
|
21 |
},
|
22 |
+
"bos_token": "<|endoftext|>",
|
23 |
"clean_up_tokenization_spaces": true,
|
24 |
+
"eos_token": "<|endoftext|>",
|
25 |
"errors": "replace",
|
26 |
"model_max_length": 1024,
|
27 |
"pad_token": "<|pad|>",
|