Delete tokenizer_config.json
Browse files- tokenizer_config.json +0 -69
tokenizer_config.json
DELETED
@@ -1,69 +0,0 @@
|
|
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": "<|end_of_turn|>",
|
31 |
-
"lstrip": false,
|
32 |
-
"normalized": false,
|
33 |
-
"rstrip": false,
|
34 |
-
"single_word": false,
|
35 |
-
"special": true
|
36 |
-
},
|
37 |
-
"32001": {
|
38 |
-
"content": "<|pad_0|>",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": false,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false,
|
43 |
-
"special": true
|
44 |
-
}
|
45 |
-
},
|
46 |
-
"additional_special_tokens": [
|
47 |
-
"<|end_of_turn|>",
|
48 |
-
"<|pad_0|>"
|
49 |
-
],
|
50 |
-
"bos_token": "<s>",
|
51 |
-
"chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
|
52 |
-
"clean_up_tokenization_spaces": false,
|
53 |
-
"eos_token": "<|end_of_turn|>",
|
54 |
-
"legacy": true,
|
55 |
-
"max_length": 1000,
|
56 |
-
"model_max_length": 1000000000000000019884624838656,
|
57 |
-
"pad_to_multiple_of": null,
|
58 |
-
"pad_token": "<|end_of_turn|>",
|
59 |
-
"pad_token_type_id": 0,
|
60 |
-
"padding_side": "left",
|
61 |
-
"sp_model_kwargs": {},
|
62 |
-
"spaces_between_special_tokens": false,
|
63 |
-
"stride": 0,
|
64 |
-
"tokenizer_class": "LlamaTokenizer",
|
65 |
-
"truncation_side": "right",
|
66 |
-
"truncation_strategy": "longest_first",
|
67 |
-
"unk_token": "<unk>",
|
68 |
-
"use_default_system_prompt": true
|
69 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|