Commit
•
60a4a92
1
Parent(s):
a2bd550
Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +21 -3
- tokenizer.json +1 -10
- tokenizer.model +3 -0
- tokenizer_config.json +24 -46
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 32000
|
3 |
+
}
|
special_tokens_map.json
CHANGED
@@ -1,6 +1,24 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"pad_token": "</s>",
|
5 |
-
"unk_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
}
|
tokenizer.json
CHANGED
@@ -9,7 +9,7 @@
|
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
12 |
-
"normalized":
|
13 |
"special": true
|
14 |
},
|
15 |
{
|
@@ -38,15 +38,6 @@
|
|
38 |
"rstrip": false,
|
39 |
"normalized": true,
|
40 |
"special": false
|
41 |
-
},
|
42 |
-
{
|
43 |
-
"id": 32001,
|
44 |
-
"content": "[PAD]",
|
45 |
-
"single_word": false,
|
46 |
-
"lstrip": true,
|
47 |
-
"rstrip": true,
|
48 |
-
"normalized": false,
|
49 |
-
"special": true
|
50 |
}
|
51 |
],
|
52 |
"normalizer": {
|
|
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
"special": true
|
14 |
},
|
15 |
{
|
|
|
38 |
"rstrip": false,
|
39 |
"normalized": true,
|
40 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
41 |
}
|
42 |
],
|
43 |
"normalizer": {
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
CHANGED
@@ -1,55 +1,33 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"1": {
|
12 |
-
"content": "<s>",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": true,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"2": {
|
20 |
-
"content": "</s>",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": true,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"32000": {
|
28 |
-
"content": "<pad>",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": true,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": false
|
34 |
-
},
|
35 |
-
"32001": {
|
36 |
-
"content": "[PAD]",
|
37 |
-
"lstrip": true,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": true,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
}
|
43 |
},
|
44 |
-
"additional_special_tokens": [],
|
45 |
-
"bos_token": "<s>",
|
46 |
"clean_up_tokenization_spaces": false,
|
47 |
-
"eos_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
"legacy": false,
|
49 |
"model_max_length": 1000000000000000019884624838656,
|
50 |
-
"pad_token":
|
51 |
"sp_model_kwargs": {},
|
52 |
"tokenizer_class": "LlamaTokenizer",
|
53 |
-
"unk_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
"use_default_system_prompt": true
|
55 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"__type": "AddedToken",
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
},
|
|
|
|
|
10 |
"clean_up_tokenization_spaces": false,
|
11 |
+
"eos_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "</s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
"legacy": false,
|
20 |
"model_max_length": 1000000000000000019884624838656,
|
21 |
+
"pad_token": null,
|
22 |
"sp_model_kwargs": {},
|
23 |
"tokenizer_class": "LlamaTokenizer",
|
24 |
+
"unk_token": {
|
25 |
+
"__type": "AddedToken",
|
26 |
+
"content": "<unk>",
|
27 |
+
"lstrip": false,
|
28 |
+
"normalized": true,
|
29 |
+
"rstrip": false,
|
30 |
+
"single_word": false
|
31 |
+
},
|
32 |
"use_default_system_prompt": true
|
33 |
}
|