Upload tokenizer
Browse files- special_tokens_map.json +35 -35
- tokenizer.model +3 -0
- tokenizer_config.json +46 -46
special_tokens_map.json
CHANGED
@@ -1,35 +1,35 @@
|
|
1 |
-
{
|
2 |
-
"additional_special_tokens": [
|
3 |
-
"<unk>",
|
4 |
-
"<s>",
|
5 |
-
"</s>"
|
6 |
-
],
|
7 |
-
"bos_token": {
|
8 |
-
"content": "<s>",
|
9 |
-
"lstrip": false,
|
10 |
-
"normalized": true,
|
11 |
-
"rstrip": false,
|
12 |
-
"single_word": false
|
13 |
-
},
|
14 |
-
"eos_token": {
|
15 |
-
"content": "</s>",
|
16 |
-
"lstrip": false,
|
17 |
-
"normalized": true,
|
18 |
-
"rstrip": false,
|
19 |
-
"single_word": false
|
20 |
-
},
|
21 |
-
"pad_token": {
|
22 |
-
"content": "</s>",
|
23 |
-
"lstrip": false,
|
24 |
-
"normalized": true,
|
25 |
-
"rstrip": false,
|
26 |
-
"single_word": false
|
27 |
-
},
|
28 |
-
"unk_token": {
|
29 |
-
"content": "<unk>",
|
30 |
-
"lstrip": false,
|
31 |
-
"normalized": true,
|
32 |
-
"rstrip": false,
|
33 |
-
"single_word": false
|
34 |
-
}
|
35 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7978987401ef447724ded0544d048831954b7517a96555ce1593149e3678b6dc
|
3 |
+
size 755169
|
tokenizer_config.json
CHANGED
@@ -1,46 +1,46 @@
|
|
1 |
-
{
|
2 |
-
"add_bos_token": true,
|
3 |
-
"add_eos_token": false,
|
4 |
-
"added_tokens_decoder": {
|
5 |
-
"0": {
|
6 |
-
"content": "<unk>",
|
7 |
-
"lstrip": false,
|
8 |
-
"normalized": true,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false,
|
11 |
-
"special": true
|
12 |
-
},
|
13 |
-
"1": {
|
14 |
-
"content": "<s>",
|
15 |
-
"lstrip": false,
|
16 |
-
"normalized": true,
|
17 |
-
"rstrip": false,
|
18 |
-
"single_word": false,
|
19 |
-
"special": true
|
20 |
-
},
|
21 |
-
"2": {
|
22 |
-
"content": "</s>",
|
23 |
-
"lstrip": false,
|
24 |
-
"normalized": true,
|
25 |
-
"rstrip": false,
|
26 |
-
"single_word": false,
|
27 |
-
"special": true
|
28 |
-
}
|
29 |
-
},
|
30 |
-
"additional_special_tokens": [
|
31 |
-
"<unk>",
|
32 |
-
"<s>",
|
33 |
-
"</s>"
|
34 |
-
],
|
35 |
-
"bos_token": "<s>",
|
36 |
-
"clean_up_tokenization_spaces": false,
|
37 |
-
"eos_token": "</s>",
|
38 |
-
"legacy": true,
|
39 |
-
"model_max_length": 1000000000000000019884624838656,
|
40 |
-
"pad_token": "</s>",
|
41 |
-
"sp_model_kwargs": {},
|
42 |
-
"spaces_between_special_tokens": false,
|
43 |
-
"tokenizer_class": "LlamaTokenizer",
|
44 |
-
"unk_token": "<unk>",
|
45 |
-
"use_default_system_prompt": true
|
46 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<unk>",
|
32 |
+
"<s>",
|
33 |
+
"</s>"
|
34 |
+
],
|
35 |
+
"bos_token": "<s>",
|
36 |
+
"clean_up_tokenization_spaces": false,
|
37 |
+
"eos_token": "</s>",
|
38 |
+
"legacy": true,
|
39 |
+
"model_max_length": 1000000000000000019884624838656,
|
40 |
+
"pad_token": "</s>",
|
41 |
+
"sp_model_kwargs": {},
|
42 |
+
"spaces_between_special_tokens": false,
|
43 |
+
"tokenizer_class": "LlamaTokenizer",
|
44 |
+
"unk_token": "<unk>",
|
45 |
+
"use_default_system_prompt": true
|
46 |
+
}
|