Upload tokenizer
Browse files- added_tokens.json +1 -2
- special_tokens_map.json +0 -14
- tokenizer_config.json +2 -10
added_tokens.json
CHANGED
@@ -1,4 +1,3 @@
|
|
1 |
{
|
2 |
-
"<|pad|>":
|
3 |
-
"<|startoftext|>": 50257
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"<|pad|>": 50257
|
|
|
3 |
}
|
special_tokens_map.json
CHANGED
@@ -1,18 +1,4 @@
|
|
1 |
{
|
2 |
-
"bos_token": {
|
3 |
-
"content": "<|startoftext|>",
|
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,
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"pad_token": {
|
3 |
"content": "<|pad|>",
|
4 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -11,14 +11,6 @@
|
|
11 |
"special": true
|
12 |
},
|
13 |
"50257": {
|
14 |
-
"content": "<|startoftext|>",
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": true,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false,
|
19 |
-
"special": true
|
20 |
-
},
|
21 |
-
"50258": {
|
22 |
"content": "<|pad|>",
|
23 |
"lstrip": false,
|
24 |
"normalized": true,
|
@@ -27,9 +19,9 @@
|
|
27 |
"special": true
|
28 |
}
|
29 |
},
|
30 |
-
"bos_token":
|
31 |
"clean_up_tokenization_spaces": true,
|
32 |
-
"eos_token":
|
33 |
"errors": "replace",
|
34 |
"model_max_length": 1024,
|
35 |
"pad_token": "<|pad|>",
|
|
|
11 |
"special": true
|
12 |
},
|
13 |
"50257": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
"content": "<|pad|>",
|
15 |
"lstrip": false,
|
16 |
"normalized": true,
|
|
|
19 |
"special": true
|
20 |
}
|
21 |
},
|
22 |
+
"bos_token": null,
|
23 |
"clean_up_tokenization_spaces": true,
|
24 |
+
"eos_token": null,
|
25 |
"errors": "replace",
|
26 |
"model_max_length": 1024,
|
27 |
"pad_token": "<|pad|>",
|