WesleySantos
commited on
Commit
•
770a7e0
1
Parent(s):
f0a7716
Upload tokenizer
Browse files- special_tokens_map.json +4 -4
- tokenizer.model +3 -0
- tokenizer_config.json +9 -4
special_tokens_map.json
CHANGED
@@ -1,21 +1,21 @@
|
|
1 |
{
|
2 |
"bos_token": {
|
3 |
-
"content": "
|
4 |
"lstrip": false,
|
5 |
"normalized": true,
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
-
"content": "
|
11 |
"lstrip": false,
|
12 |
"normalized": true,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token": "
|
17 |
"unk_token": {
|
18 |
-
"content": "
|
19 |
"lstrip": false,
|
20 |
"normalized": true,
|
21 |
"rstrip": false,
|
|
|
1 |
{
|
2 |
"bos_token": {
|
3 |
+
"content": "",
|
4 |
"lstrip": false,
|
5 |
"normalized": true,
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
+
"content": "",
|
11 |
"lstrip": false,
|
12 |
"normalized": true,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
"unk_token": {
|
18 |
+
"content": "",
|
19 |
"lstrip": false,
|
20 |
"normalized": true,
|
21 |
"rstrip": false,
|
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
@@ -1,7 +1,9 @@
|
|
1 |
{
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"__type": "AddedToken",
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
"normalized": true,
|
7 |
"rstrip": false,
|
@@ -10,22 +12,25 @@
|
|
10 |
"clean_up_tokenization_spaces": false,
|
11 |
"eos_token": {
|
12 |
"__type": "AddedToken",
|
13 |
-
"content": "
|
14 |
"lstrip": false,
|
15 |
"normalized": true,
|
16 |
"rstrip": false,
|
17 |
"single_word": false
|
18 |
},
|
|
|
19 |
"model_max_length": 1000000000000000019884624838656,
|
20 |
"pad_token": null,
|
21 |
"sp_model_kwargs": {},
|
|
|
22 |
"tokenizer_class": "LlamaTokenizer",
|
23 |
"unk_token": {
|
24 |
"__type": "AddedToken",
|
25 |
-
"content": "
|
26 |
"lstrip": false,
|
27 |
"normalized": true,
|
28 |
"rstrip": false,
|
29 |
"single_word": false
|
30 |
-
}
|
|
|
31 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"bos_token": {
|
5 |
"__type": "AddedToken",
|
6 |
+
"content": "",
|
7 |
"lstrip": false,
|
8 |
"normalized": true,
|
9 |
"rstrip": false,
|
|
|
12 |
"clean_up_tokenization_spaces": false,
|
13 |
"eos_token": {
|
14 |
"__type": "AddedToken",
|
15 |
+
"content": "",
|
16 |
"lstrip": false,
|
17 |
"normalized": true,
|
18 |
"rstrip": false,
|
19 |
"single_word": false
|
20 |
},
|
21 |
+
"legacy": null,
|
22 |
"model_max_length": 1000000000000000019884624838656,
|
23 |
"pad_token": null,
|
24 |
"sp_model_kwargs": {},
|
25 |
+
"spaces_between_special_tokens": false,
|
26 |
"tokenizer_class": "LlamaTokenizer",
|
27 |
"unk_token": {
|
28 |
"__type": "AddedToken",
|
29 |
+
"content": "",
|
30 |
"lstrip": false,
|
31 |
"normalized": true,
|
32 |
"rstrip": false,
|
33 |
"single_word": false
|
34 |
+
},
|
35 |
+
"use_default_system_prompt": true
|
36 |
}
|