lleticiasilvaa
commited on
Commit
•
1391ac1
1
Parent(s):
c96c0af
Upload tokenizer
Browse files- added_tokens.json +6 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +84 -0
added_tokens.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[/QUESTION]": 32003,
|
3 |
+
"[/SQL]": 32001,
|
4 |
+
"[QUESTION]": 32002,
|
5 |
+
"[SQL]": 32000
|
6 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"[SQL]",
|
4 |
+
"[/SQL]",
|
5 |
+
"[QUESTION]",
|
6 |
+
"[/QUESTION]"
|
7 |
+
],
|
8 |
+
"bos_token": {
|
9 |
+
"content": "<s>",
|
10 |
+
"lstrip": false,
|
11 |
+
"normalized": false,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
},
|
15 |
+
"eos_token": {
|
16 |
+
"content": "</s>",
|
17 |
+
"lstrip": false,
|
18 |
+
"normalized": false,
|
19 |
+
"rstrip": false,
|
20 |
+
"single_word": false
|
21 |
+
},
|
22 |
+
"pad_token": "</s>",
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "[SQL]",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "[/SQL]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "[QUESTION]",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "[/QUESTION]",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
}
|
61 |
+
},
|
62 |
+
"additional_special_tokens": [
|
63 |
+
"[SQL]",
|
64 |
+
"[/SQL]",
|
65 |
+
"[QUESTION]",
|
66 |
+
"[/QUESTION]"
|
67 |
+
],
|
68 |
+
"bos_token": "<s>",
|
69 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are an SQL expert tasked with answering questions about an SQLite database.\nYour responses must always consist of valid SQL code and only that.' %}{% endif %}{{ '# <|system|>\n' + system_message + '\n\n' }}{% if messages|selectattr(\"role\", \"equalto\", \"example\")|list %}Below are some examples of question and their corresponding SQL queries:\n\n{% else %}\n{% endif %}{% for message in loop_messages %}{% if message['role'] == 'example' %}{{ message['content'] }}\n\n{% elif message['role'] == 'schema' %}# <|schema|>\nThe query will run on a database with the following schema:\n{{ message['content'] }}\n\n{% elif message['role'] == 'user' %}# <|user|>\n[QUESTION]{{ message['content'] }}[/QUESTION]\n\n{% elif message['role'] == 'assistant' %}# <|assistant|>\n[SQL]{{ message['content'] }}[/SQL]{% endif %}{% endfor %}{% if add_generation_prompt %}# <|assistant|>\n[SQL]{% endif %}",
|
70 |
+
"clean_up_tokenization_spaces": false,
|
71 |
+
"eos_token": "</s>",
|
72 |
+
"legacy": false,
|
73 |
+
"max_length": 2048,
|
74 |
+
"model_max_length": 2048,
|
75 |
+
"pad_token": "</s>",
|
76 |
+
"padding_side": "right",
|
77 |
+
"sp_model_kwargs": {},
|
78 |
+
"stride": 0,
|
79 |
+
"tokenizer_class": "LlamaTokenizer",
|
80 |
+
"truncation_side": "right",
|
81 |
+
"truncation_strategy": "longest_first",
|
82 |
+
"unk_token": "<unk>",
|
83 |
+
"use_default_system_prompt": false
|
84 |
+
}
|