Locutusque
commited on
Commit
•
f7d7325
1
Parent(s):
9473e24
Upload 3 files
Browse files- special_tokens_map.json +4 -0
- tokenizer.json +26 -8
- tokenizer_config.json +24 -1
special_tokens_map.json
CHANGED
@@ -1,4 +1,8 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<|bos|>",
|
4 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|ASSISTANT|>",
|
4 |
+
"<|USER|>"
|
5 |
+
],
|
6 |
"bos_token": {
|
7 |
"content": "<|bos|>",
|
8 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
@@ -61,6 +61,24 @@
|
|
61 |
"rstrip": false,
|
62 |
"normalized": false,
|
63 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
}
|
65 |
],
|
66 |
"normalizer": {
|
@@ -85,7 +103,7 @@
|
|
85 |
"single": [
|
86 |
{
|
87 |
"SpecialToken": {
|
88 |
-
"id": "
|
89 |
"type_id": 0
|
90 |
}
|
91 |
},
|
@@ -99,7 +117,7 @@
|
|
99 |
"pair": [
|
100 |
{
|
101 |
"SpecialToken": {
|
102 |
-
"id": "
|
103 |
"type_id": 0
|
104 |
}
|
105 |
},
|
@@ -111,7 +129,7 @@
|
|
111 |
},
|
112 |
{
|
113 |
"SpecialToken": {
|
114 |
-
"id": "
|
115 |
"type_id": 1
|
116 |
}
|
117 |
},
|
@@ -123,13 +141,13 @@
|
|
123 |
}
|
124 |
],
|
125 |
"special_tokens": {
|
126 |
-
"
|
127 |
-
"id": "
|
128 |
"ids": [
|
129 |
-
|
130 |
],
|
131 |
"tokens": [
|
132 |
-
"
|
133 |
]
|
134 |
}
|
135 |
}
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 512,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
|
|
61 |
"rstrip": false,
|
62 |
"normalized": false,
|
63 |
"special": true
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"id": 32003,
|
67 |
+
"content": "<|ASSISTANT|>",
|
68 |
+
"single_word": false,
|
69 |
+
"lstrip": false,
|
70 |
+
"rstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"special": true
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"id": 32004,
|
76 |
+
"content": "<|USER|>",
|
77 |
+
"single_word": false,
|
78 |
+
"lstrip": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"special": true
|
82 |
}
|
83 |
],
|
84 |
"normalizer": {
|
|
|
103 |
"single": [
|
104 |
{
|
105 |
"SpecialToken": {
|
106 |
+
"id": "<|bos|>",
|
107 |
"type_id": 0
|
108 |
}
|
109 |
},
|
|
|
117 |
"pair": [
|
118 |
{
|
119 |
"SpecialToken": {
|
120 |
+
"id": "<|bos|>",
|
121 |
"type_id": 0
|
122 |
}
|
123 |
},
|
|
|
129 |
},
|
130 |
{
|
131 |
"SpecialToken": {
|
132 |
+
"id": "<|bos|>",
|
133 |
"type_id": 1
|
134 |
}
|
135 |
},
|
|
|
141 |
}
|
142 |
],
|
143 |
"special_tokens": {
|
144 |
+
"<|bos|>": {
|
145 |
+
"id": "<|bos|>",
|
146 |
"ids": [
|
147 |
+
32000
|
148 |
],
|
149 |
"tokens": [
|
150 |
+
"<|bos|>"
|
151 |
]
|
152 |
}
|
153 |
}
|
tokenizer_config.json
CHANGED
@@ -47,18 +47,41 @@
|
|
47 |
"rstrip": false,
|
48 |
"single_word": false,
|
49 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
}
|
51 |
},
|
52 |
-
"additional_special_tokens": [
|
|
|
|
|
|
|
53 |
"bos_token": "<|bos|>",
|
54 |
"clean_up_tokenization_spaces": false,
|
55 |
"eos_token": "<|endoftext|>",
|
56 |
"legacy": true,
|
|
|
57 |
"model_max_length": 1000000000000000019884624838656,
|
58 |
"pad_token": "[PAD]",
|
59 |
"sp_model_kwargs": {},
|
60 |
"spaces_between_special_tokens": false,
|
|
|
61 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
62 |
"unk_token": "<unk>",
|
63 |
"use_default_system_prompt": true
|
64 |
}
|
|
|
47 |
"rstrip": false,
|
48 |
"single_word": false,
|
49 |
"special": true
|
50 |
+
},
|
51 |
+
"32003": {
|
52 |
+
"content": "<|ASSISTANT|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"32004": {
|
60 |
+
"content": "<|USER|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
}
|
67 |
},
|
68 |
+
"additional_special_tokens": [
|
69 |
+
"<|ASSISTANT|>",
|
70 |
+
"<|USER|>"
|
71 |
+
],
|
72 |
"bos_token": "<|bos|>",
|
73 |
"clean_up_tokenization_spaces": false,
|
74 |
"eos_token": "<|endoftext|>",
|
75 |
"legacy": true,
|
76 |
+
"max_length": 1536,
|
77 |
"model_max_length": 1000000000000000019884624838656,
|
78 |
"pad_token": "[PAD]",
|
79 |
"sp_model_kwargs": {},
|
80 |
"spaces_between_special_tokens": false,
|
81 |
+
"stride": 0,
|
82 |
"tokenizer_class": "LlamaTokenizer",
|
83 |
+
"truncation_side": "right",
|
84 |
+
"truncation_strategy": "longest_first",
|
85 |
"unk_token": "<unk>",
|
86 |
"use_default_system_prompt": true
|
87 |
}
|