Commit
•
356707e
1
Parent(s):
ee21a37
Upload tokenizer
Browse files- special_tokens_map.json +4 -31
- tokenizer_config.json +6 -36
- vocab.json +0 -0
special_tokens_map.json
CHANGED
@@ -1,48 +1,21 @@
|
|
1 |
{
|
2 |
"bos_token": {
|
3 |
-
"content": "
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": true,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"cls_token": {
|
10 |
-
"content": "<s>",
|
11 |
"lstrip": false,
|
12 |
"normalized": true,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
"eos_token": {
|
17 |
-
"content": "
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": true,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"mask_token": {
|
24 |
-
"content": "<mask>",
|
25 |
-
"lstrip": true,
|
26 |
-
"normalized": true,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
-
"pad_token": {
|
31 |
-
"content": "<pad>",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": true,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
},
|
37 |
-
"sep_token": {
|
38 |
-
"content": "</s>",
|
39 |
"lstrip": false,
|
40 |
"normalized": true,
|
41 |
"rstrip": false,
|
42 |
"single_word": false
|
43 |
},
|
|
|
44 |
"unk_token": {
|
45 |
-
"content": "
|
46 |
"lstrip": false,
|
47 |
"normalized": true,
|
48 |
"rstrip": 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": "<|endoftext|>",
|
17 |
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
"lstrip": false,
|
20 |
"normalized": true,
|
21 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
@@ -1,60 +1,30 @@
|
|
1 |
{
|
|
|
2 |
"add_prefix_space": false,
|
3 |
"bos_token": {
|
4 |
"__type": "AddedToken",
|
5 |
-
"content": "
|
6 |
"lstrip": false,
|
7 |
"normalized": true,
|
8 |
"rstrip": false,
|
9 |
"single_word": false
|
10 |
},
|
11 |
"clean_up_tokenization_spaces": true,
|
12 |
-
"cls_token": {
|
13 |
-
"__type": "AddedToken",
|
14 |
-
"content": "<s>",
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": true,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false
|
19 |
-
},
|
20 |
"eos_token": {
|
21 |
"__type": "AddedToken",
|
22 |
-
"content": "
|
23 |
"lstrip": false,
|
24 |
"normalized": true,
|
25 |
"rstrip": false,
|
26 |
"single_word": false
|
27 |
},
|
28 |
"errors": "replace",
|
29 |
-
"mask_token": {
|
30 |
-
"__type": "AddedToken",
|
31 |
-
"content": "<mask>",
|
32 |
-
"lstrip": true,
|
33 |
-
"normalized": true,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
},
|
37 |
"model_max_length": 1024,
|
38 |
-
"pad_token":
|
39 |
-
|
40 |
-
"content": "<pad>",
|
41 |
-
"lstrip": false,
|
42 |
-
"normalized": true,
|
43 |
-
"rstrip": false,
|
44 |
-
"single_word": false
|
45 |
-
},
|
46 |
-
"sep_token": {
|
47 |
-
"__type": "AddedToken",
|
48 |
-
"content": "</s>",
|
49 |
-
"lstrip": false,
|
50 |
-
"normalized": true,
|
51 |
-
"rstrip": false,
|
52 |
-
"single_word": false
|
53 |
-
},
|
54 |
-
"tokenizer_class": "BartTokenizer",
|
55 |
"unk_token": {
|
56 |
"__type": "AddedToken",
|
57 |
-
"content": "
|
58 |
"lstrip": false,
|
59 |
"normalized": true,
|
60 |
"rstrip": false,
|
|
|
1 |
{
|
2 |
+
"add_bos_token": false,
|
3 |
"add_prefix_space": false,
|
4 |
"bos_token": {
|
5 |
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
"lstrip": false,
|
8 |
"normalized": true,
|
9 |
"rstrip": false,
|
10 |
"single_word": false
|
11 |
},
|
12 |
"clean_up_tokenization_spaces": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
"eos_token": {
|
14 |
"__type": "AddedToken",
|
15 |
+
"content": "<|endoftext|>",
|
16 |
"lstrip": false,
|
17 |
"normalized": true,
|
18 |
"rstrip": false,
|
19 |
"single_word": false
|
20 |
},
|
21 |
"errors": "replace",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
"model_max_length": 1024,
|
23 |
+
"pad_token": null,
|
24 |
+
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
"unk_token": {
|
26 |
"__type": "AddedToken",
|
27 |
+
"content": "<|endoftext|>",
|
28 |
"lstrip": false,
|
29 |
"normalized": true,
|
30 |
"rstrip": false,
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|