Upload tokenizer
Browse files- added_tokens.json +13 -0
- special_tokens_map.json +63 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +147 -0
added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 61366,
|
3 |
+
"<|/context|>": 61371,
|
4 |
+
"<|assistant|>": 61369,
|
5 |
+
"<|context|>": 61370,
|
6 |
+
"<|system|>": 61367,
|
7 |
+
"<|tldr|>": 61376,
|
8 |
+
"<|translate-el-en|>": 61375,
|
9 |
+
"<|translate-en-el|>": 61374,
|
10 |
+
"<|user|>": 61368,
|
11 |
+
"[/INST]": 61373,
|
12 |
+
"[INST]": 61372
|
13 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|system|>",
|
4 |
+
"<|user|>",
|
5 |
+
"<|assistant|>",
|
6 |
+
"<|context|>",
|
7 |
+
"<|/context|>",
|
8 |
+
"[INST]",
|
9 |
+
"[/INST]",
|
10 |
+
"<|translate-en-el|>",
|
11 |
+
"<|translate-el-en|>",
|
12 |
+
"<|tldr|>"
|
13 |
+
],
|
14 |
+
"bos_token": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"cls_token": {
|
22 |
+
"content": "<s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"eos_token": {
|
29 |
+
"content": "</s>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
},
|
35 |
+
"mask_token": {
|
36 |
+
"content": "<unk>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false
|
41 |
+
},
|
42 |
+
"pad_token": {
|
43 |
+
"content": "<pad>",
|
44 |
+
"lstrip": false,
|
45 |
+
"normalized": false,
|
46 |
+
"rstrip": false,
|
47 |
+
"single_word": false
|
48 |
+
},
|
49 |
+
"sep_token": {
|
50 |
+
"content": "</s>",
|
51 |
+
"lstrip": false,
|
52 |
+
"normalized": false,
|
53 |
+
"rstrip": false,
|
54 |
+
"single_word": false
|
55 |
+
},
|
56 |
+
"unk_token": {
|
57 |
+
"content": "<unk>",
|
58 |
+
"lstrip": false,
|
59 |
+
"normalized": false,
|
60 |
+
"rstrip": false,
|
61 |
+
"single_word": false
|
62 |
+
}
|
63 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:531c02ac6d66e23eb0269bc8c396094abc612491af242b731cf0ffb42a769aa4
|
3 |
+
size 1180082
|
tokenizer_config.json
ADDED
@@ -0,0 +1,147 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"61366": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"61367": {
|
39 |
+
"content": "<|system|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": true,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": true,
|
44 |
+
"special": true
|
45 |
+
},
|
46 |
+
"61368": {
|
47 |
+
"content": "<|user|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": true,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": true,
|
52 |
+
"special": true
|
53 |
+
},
|
54 |
+
"61369": {
|
55 |
+
"content": "<|assistant|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": true,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": true,
|
60 |
+
"special": true
|
61 |
+
},
|
62 |
+
"61370": {
|
63 |
+
"content": "<|context|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": true,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": true,
|
68 |
+
"special": true
|
69 |
+
},
|
70 |
+
"61371": {
|
71 |
+
"content": "<|/context|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": true,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": true,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"61372": {
|
79 |
+
"content": "[INST]",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": true,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": true,
|
84 |
+
"special": true
|
85 |
+
},
|
86 |
+
"61373": {
|
87 |
+
"content": "[/INST]",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": true,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": true,
|
92 |
+
"special": true
|
93 |
+
},
|
94 |
+
"61374": {
|
95 |
+
"content": "<|translate-en-el|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": true,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": true,
|
100 |
+
"special": true
|
101 |
+
},
|
102 |
+
"61375": {
|
103 |
+
"content": "<|translate-el-en|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": true,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": true,
|
108 |
+
"special": true
|
109 |
+
},
|
110 |
+
"61376": {
|
111 |
+
"content": "<|tldr|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": true,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": true,
|
116 |
+
"special": true
|
117 |
+
}
|
118 |
+
},
|
119 |
+
"additional_special_tokens": [
|
120 |
+
"<|system|>",
|
121 |
+
"<|user|>",
|
122 |
+
"<|assistant|>",
|
123 |
+
"<|context|>",
|
124 |
+
"<|/context|>",
|
125 |
+
"[INST]",
|
126 |
+
"[/INST]",
|
127 |
+
"<|translate-en-el|>",
|
128 |
+
"<|translate-el-en|>",
|
129 |
+
"<|tldr|>"
|
130 |
+
],
|
131 |
+
"bos_token": "<s>",
|
132 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
133 |
+
"clean_up_tokenization_spaces": false,
|
134 |
+
"cls_token": "<s>",
|
135 |
+
"eos_token": "</s>",
|
136 |
+
"legacy": true,
|
137 |
+
"mask_token": "<unk>",
|
138 |
+
"model_max_length": 1000000000000000019884624838656,
|
139 |
+
"pad_token": "<pad>",
|
140 |
+
"sep_token": "</s>",
|
141 |
+
"sp_model_kwargs": {},
|
142 |
+
"spaces_between_special_tokens": false,
|
143 |
+
"tokenizer_class": "LlamaTokenizer",
|
144 |
+
"unk_token": "<unk>",
|
145 |
+
"use_default_system_prompt": false,
|
146 |
+
"use_fast": true
|
147 |
+
}
|