Upload tokenizer
Browse files- added_tokens.json +3 -12
- merges.txt +0 -0
- special_tokens_map.json +5 -15
- tokenizer.json +0 -0
- tokenizer_config.json +18 -114
- vocab.json +0 -0
added_tokens.json
CHANGED
@@ -1,14 +1,5 @@
|
|
1 |
{
|
2 |
-
"<|
|
3 |
-
"<|
|
4 |
-
"<|
|
5 |
-
"<|eot_id|>": 32011,
|
6 |
-
"<|placeholder1|>": 32002,
|
7 |
-
"<|placeholder2|>": 32003,
|
8 |
-
"<|placeholder3|>": 32004,
|
9 |
-
"<|placeholder4|>": 32005,
|
10 |
-
"<|placeholder5|>": 32008,
|
11 |
-
"<|placeholder6|>": 32009,
|
12 |
-
"<|system|>": 32006,
|
13 |
-
"<|user|>": 32010
|
14 |
}
|
|
|
1 |
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
CHANGED
@@ -1,13 +1,10 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
"eos_token": {
|
10 |
-
"content": "<|
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
@@ -19,12 +16,5 @@
|
|
19 |
"normalized": false,
|
20 |
"rstrip": false,
|
21 |
"single_word": false
|
22 |
-
},
|
23 |
-
"unk_token": {
|
24 |
-
"content": "<unk>",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": false,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
}
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
|
|
|
|
|
|
6 |
"eos_token": {
|
7 |
+
"content": "<|im_end|>",
|
8 |
"lstrip": false,
|
9 |
"normalized": false,
|
10 |
"rstrip": false,
|
|
|
16 |
"normalized": false,
|
17 |
"rstrip": false,
|
18 |
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
}
|
20 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,33 +1,7 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"add_eos_token": false,
|
4 |
-
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
6 |
-
"
|
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": true,
|
27 |
-
"single_word": false,
|
28 |
-
"special": false
|
29 |
-
},
|
30 |
-
"32000": {
|
31 |
"content": "<|endoftext|>",
|
32 |
"lstrip": false,
|
33 |
"normalized": false,
|
@@ -35,88 +9,16 @@
|
|
35 |
"single_word": false,
|
36 |
"special": true
|
37 |
},
|
38 |
-
"
|
39 |
-
"content": "<|
|
40 |
-
"lstrip": false,
|
41 |
-
"normalized": false,
|
42 |
-
"rstrip": true,
|
43 |
-
"single_word": false,
|
44 |
-
"special": true
|
45 |
-
},
|
46 |
-
"32002": {
|
47 |
-
"content": "<|placeholder1|>",
|
48 |
-
"lstrip": false,
|
49 |
-
"normalized": false,
|
50 |
-
"rstrip": true,
|
51 |
-
"single_word": false,
|
52 |
-
"special": true
|
53 |
-
},
|
54 |
-
"32003": {
|
55 |
-
"content": "<|placeholder2|>",
|
56 |
-
"lstrip": false,
|
57 |
-
"normalized": false,
|
58 |
-
"rstrip": true,
|
59 |
-
"single_word": false,
|
60 |
-
"special": true
|
61 |
-
},
|
62 |
-
"32004": {
|
63 |
-
"content": "<|placeholder3|>",
|
64 |
"lstrip": false,
|
65 |
"normalized": false,
|
66 |
-
"rstrip":
|
67 |
-
"single_word": false,
|
68 |
-
"special": true
|
69 |
-
},
|
70 |
-
"32005": {
|
71 |
-
"content": "<|placeholder4|>",
|
72 |
-
"lstrip": false,
|
73 |
-
"normalized": false,
|
74 |
-
"rstrip": true,
|
75 |
-
"single_word": false,
|
76 |
-
"special": true
|
77 |
-
},
|
78 |
-
"32006": {
|
79 |
-
"content": "<|system|>",
|
80 |
-
"lstrip": false,
|
81 |
-
"normalized": false,
|
82 |
-
"rstrip": true,
|
83 |
-
"single_word": false,
|
84 |
-
"special": true
|
85 |
-
},
|
86 |
-
"32007": {
|
87 |
-
"content": "<|end|>",
|
88 |
-
"lstrip": false,
|
89 |
-
"normalized": false,
|
90 |
-
"rstrip": true,
|
91 |
-
"single_word": false,
|
92 |
-
"special": true
|
93 |
-
},
|
94 |
-
"32008": {
|
95 |
-
"content": "<|placeholder5|>",
|
96 |
-
"lstrip": false,
|
97 |
-
"normalized": false,
|
98 |
-
"rstrip": true,
|
99 |
-
"single_word": false,
|
100 |
-
"special": true
|
101 |
-
},
|
102 |
-
"32009": {
|
103 |
-
"content": "<|placeholder6|>",
|
104 |
-
"lstrip": false,
|
105 |
-
"normalized": false,
|
106 |
-
"rstrip": true,
|
107 |
-
"single_word": false,
|
108 |
-
"special": true
|
109 |
-
},
|
110 |
-
"32010": {
|
111 |
-
"content": "<|user|>",
|
112 |
-
"lstrip": false,
|
113 |
-
"normalized": false,
|
114 |
-
"rstrip": true,
|
115 |
"single_word": false,
|
116 |
"special": true
|
117 |
},
|
118 |
-
"
|
119 |
-
"content": "<|
|
120 |
"lstrip": false,
|
121 |
"normalized": false,
|
122 |
"rstrip": false,
|
@@ -124,17 +26,19 @@
|
|
124 |
"special": true
|
125 |
}
|
126 |
},
|
127 |
-
"
|
128 |
-
|
|
|
|
|
|
|
|
|
129 |
"clean_up_tokenization_spaces": false,
|
130 |
-
"eos_token": "<|
|
131 |
-
"
|
132 |
-
"model_max_length":
|
133 |
"pad_token": "<|endoftext|>",
|
134 |
"padding_side": "left",
|
135 |
-
"sp_model_kwargs": {},
|
136 |
"split_special_tokens": false,
|
137 |
-
"tokenizer_class": "
|
138 |
-
"unk_token":
|
139 |
-
"use_default_system_prompt": false
|
140 |
}
|
|
|
1 |
{
|
2 |
+
"add_prefix_space": false,
|
|
|
|
|
3 |
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"content": "<|endoftext|>",
|
6 |
"lstrip": false,
|
7 |
"normalized": false,
|
|
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
"lstrip": false,
|
15 |
"normalized": false,
|
16 |
+
"rstrip": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
"lstrip": false,
|
23 |
"normalized": false,
|
24 |
"rstrip": false,
|
|
|
26 |
"special": true
|
27 |
}
|
28 |
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:\n' + content + '\n\n### Response:\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n\n' }}{% endif %}{% endfor %}",
|
35 |
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|im_end|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 32768,
|
39 |
"pad_token": "<|endoftext|>",
|
40 |
"padding_side": "left",
|
|
|
41 |
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
43 |
+
"unk_token": null
|
|
|
44 |
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|