Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +53 -0
tokenizer_config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"32000": {
|
31 |
+
"content": "[PAD]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
}
|
38 |
+
},
|
39 |
+
"additional_special_tokens": [],
|
40 |
+
"bos_token": "<s>",
|
41 |
+
"chat_template": "{% for message in messages %}\n {% if message['role'] == 'user' %}\n {{'<user> ' + message['content'].strip() + ' </user>' }}\n {% elif message['role'] == 'system' %}\n {{'<system>\\n' + message['content'].strip() + '\\n</system>\\n\\n' }}\n {% elif message['role'] == 'assistant' %}\n {{ message['content'].strip() + ' </assistant>' + eos_token }}\n {% elif message['role'] == 'input' %}\n {{'<input> ' + message['content'] + ' </input>' }}\n {% endif %}\n{% endfor %}",
|
42 |
+
"clean_up_tokenization_spaces": false,
|
43 |
+
"do_lower_case": false,
|
44 |
+
"eos_token": "</s>",
|
45 |
+
"legacy": true,
|
46 |
+
"model_max_length": 4096,
|
47 |
+
"pad_token": "[PAD]",
|
48 |
+
"sp_model_kwargs": {},
|
49 |
+
"spaces_between_special_tokens": false,
|
50 |
+
"tokenizer_class": "LlamaTokenizer",
|
51 |
+
"unk_token": "<unk>",
|
52 |
+
"use_default_system_prompt": false
|
53 |
+
}
|