Upload tokenizer
Browse files- special_tokens_map.json +28 -4
- tokenizer.json +16 -2
- tokenizer_config.json +9 -0
special_tokens_map.json
CHANGED
@@ -4,8 +4,32 @@
|
|
4 |
"<s>",
|
5 |
"</s>"
|
6 |
],
|
7 |
-
"bos_token":
|
8 |
-
|
9 |
-
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
}
|
|
|
4 |
"<s>",
|
5 |
"</s>"
|
6 |
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
}
|
tokenizer.json
CHANGED
@@ -1,7 +1,21 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 8192,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": {
|
11 |
+
"Fixed": 8192
|
12 |
+
},
|
13 |
+
"direction": "Left",
|
14 |
+
"pad_to_multiple_of": null,
|
15 |
+
"pad_id": 2,
|
16 |
+
"pad_type_id": 0,
|
17 |
+
"pad_token": "</s>"
|
18 |
+
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
@@ -35,11 +37,18 @@
|
|
35 |
"clean_up_tokenization_spaces": false,
|
36 |
"eos_token": "</s>",
|
37 |
"legacy": false,
|
|
|
38 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
39 |
"pad_token": "</s>",
|
|
|
|
|
40 |
"sp_model_kwargs": {},
|
41 |
"spaces_between_special_tokens": false,
|
|
|
42 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
43 |
"unk_token": "<unk>",
|
44 |
"use_default_system_prompt": true
|
45 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
37 |
"clean_up_tokenization_spaces": false,
|
38 |
"eos_token": "</s>",
|
39 |
"legacy": false,
|
40 |
+
"max_length": 8192,
|
41 |
"model_max_length": 1000000000000000019884624838656,
|
42 |
+
"pad_to_multiple_of": null,
|
43 |
"pad_token": "</s>",
|
44 |
+
"pad_token_type_id": 0,
|
45 |
+
"padding_side": "left",
|
46 |
"sp_model_kwargs": {},
|
47 |
"spaces_between_special_tokens": false,
|
48 |
+
"stride": 0,
|
49 |
"tokenizer_class": "LlamaTokenizer",
|
50 |
+
"truncation_side": "right",
|
51 |
+
"truncation_strategy": "longest_first",
|
52 |
"unk_token": "<unk>",
|
53 |
"use_default_system_prompt": true
|
54 |
}
|