huseinzol05
commited on
Commit
•
5d868bb
1
Parent(s):
f02408c
Upload tokenizer
Browse files- tokenizer.json +2 -35
- tokenizer_config.json +3 -5
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 16384,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
@@ -56,12 +51,6 @@
|
|
56 |
"post_processor": {
|
57 |
"type": "TemplateProcessing",
|
58 |
"single": [
|
59 |
-
{
|
60 |
-
"SpecialToken": {
|
61 |
-
"id": "<s>",
|
62 |
-
"type_id": 0
|
63 |
-
}
|
64 |
-
},
|
65 |
{
|
66 |
"Sequence": {
|
67 |
"id": "A",
|
@@ -70,24 +59,12 @@
|
|
70 |
}
|
71 |
],
|
72 |
"pair": [
|
73 |
-
{
|
74 |
-
"SpecialToken": {
|
75 |
-
"id": "<s>",
|
76 |
-
"type_id": 0
|
77 |
-
}
|
78 |
-
},
|
79 |
{
|
80 |
"Sequence": {
|
81 |
"id": "A",
|
82 |
"type_id": 0
|
83 |
}
|
84 |
},
|
85 |
-
{
|
86 |
-
"SpecialToken": {
|
87 |
-
"id": "<s>",
|
88 |
-
"type_id": 1
|
89 |
-
}
|
90 |
-
},
|
91 |
{
|
92 |
"Sequence": {
|
93 |
"id": "B",
|
@@ -95,17 +72,7 @@
|
|
95 |
}
|
96 |
}
|
97 |
],
|
98 |
-
"special_tokens": {
|
99 |
-
"<s>": {
|
100 |
-
"id": "<s>",
|
101 |
-
"ids": [
|
102 |
-
1
|
103 |
-
],
|
104 |
-
"tokens": [
|
105 |
-
"<s>"
|
106 |
-
]
|
107 |
-
}
|
108 |
-
}
|
109 |
},
|
110 |
"decoder": {
|
111 |
"type": "Sequence",
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
51 |
"post_processor": {
|
52 |
"type": "TemplateProcessing",
|
53 |
"single": [
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
{
|
55 |
"Sequence": {
|
56 |
"id": "A",
|
|
|
59 |
}
|
60 |
],
|
61 |
"pair": [
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
{
|
63 |
"Sequence": {
|
64 |
"id": "A",
|
65 |
"type_id": 0
|
66 |
}
|
67 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
{
|
69 |
"Sequence": {
|
70 |
"id": "B",
|
|
|
72 |
}
|
73 |
}
|
74 |
],
|
75 |
+
"special_tokens": {}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
},
|
77 |
"decoder": {
|
78 |
"type": "Sequence",
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
@@ -26,19 +28,15 @@
|
|
26 |
}
|
27 |
},
|
28 |
"bos_token": "<s>",
|
29 |
-
"chat_template": "{
|
30 |
"clean_up_tokenization_spaces": false,
|
31 |
"eos_token": "</s>",
|
32 |
"legacy": false,
|
33 |
-
"max_length": 16384,
|
34 |
"model_max_length": 1000000000000000019884624838656,
|
35 |
"pad_token": "<unk>",
|
36 |
"padding_side": "right",
|
37 |
"sp_model_kwargs": {},
|
38 |
-
"stride": 0,
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
40 |
-
"truncation_side": "right",
|
41 |
-
"truncation_strategy": "longest_first",
|
42 |
"unk_token": "<unk>",
|
43 |
"use_default_system_prompt": false
|
44 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
28 |
}
|
29 |
},
|
30 |
"bos_token": "<s>",
|
31 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": false,
|
|
|
35 |
"model_max_length": 1000000000000000019884624838656,
|
36 |
"pad_token": "<unk>",
|
37 |
"padding_side": "right",
|
38 |
"sp_model_kwargs": {},
|
|
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
40 |
"unk_token": "<unk>",
|
41 |
"use_default_system_prompt": false
|
42 |
}
|