Upload tokenizer
Browse files- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +108 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "[INST]",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"4": {
|
38 |
+
"content": "[/INST]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"5": {
|
46 |
+
"content": "[TOOL_CALLS]",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": true,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"6": {
|
54 |
+
"content": "[AVAILABLE_TOOLS]",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": true,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"7": {
|
62 |
+
"content": "[/AVAILABLE_TOOLS]",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": true,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"8": {
|
70 |
+
"content": "[TOOL_RESULTS]",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": true,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"9": {
|
78 |
+
"content": "[/TOOL_RESULTS]",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": true,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
}
|
85 |
+
},
|
86 |
+
"additional_special_tokens": [],
|
87 |
+
"bos_token": "<s>",
|
88 |
+
"chat_template": [
|
89 |
+
{
|
90 |
+
"name": "default",
|
91 |
+
"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 %}"
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"name": "tool_use",
|
95 |
+
"template": "{{bos_token}}{% set user_messages = messages | selectattr('role', 'equalto', 'user') | list %}{% for message in messages %}{% if message['role'] == 'user' %}{% if message == user_messages[-1] %}{% if tools %}{{'[AVAILABLE_TOOLS]'+ tools|string + '[/AVAILABLE_TOOLS]'}}{% endif %}{{ '[INST]' + message['content'] + '[/INST]' }}{% else %}{{ '[INST]' + message['content'] + '[/INST]' }}{% endif %}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + ' ' + eos_token}}{% elif message['role'] == 'tool_results' %}{{'[TOOL_RESULTS]' + message['content']|string + '[/TOOL_RESULTS]'}}{% elif message['role'] == 'tool_calls' %}{{'[TOOL_CALLS]' + message['content']|string + eos_token}}{% endif %}{% endfor %}"
|
96 |
+
}
|
97 |
+
],
|
98 |
+
"clean_up_tokenization_spaces": false,
|
99 |
+
"eos_token": "</s>",
|
100 |
+
"legacy": true,
|
101 |
+
"model_max_length": 1000000000000000019884624838656,
|
102 |
+
"pad_token": null,
|
103 |
+
"sp_model_kwargs": {},
|
104 |
+
"spaces_between_special_tokens": false,
|
105 |
+
"tokenizer_class": "LlamaTokenizer",
|
106 |
+
"unk_token": "<unk>",
|
107 |
+
"use_default_system_prompt": false
|
108 |
+
}
|