huseinzol05
commited on
Commit
•
ef848a8
1
Parent(s):
cbb0084
Upload tokenizer
Browse files- special_tokens_map.json +36 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<pad>",
|
4 |
+
"<s>",
|
5 |
+
"</s>",
|
6 |
+
"<unk>"
|
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": {
|
23 |
+
"content": "<pad>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
},
|
29 |
+
"unk_token": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
}
|
36 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<pad>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"additional_special_tokens": [
|
37 |
+
"<pad>",
|
38 |
+
"<s>",
|
39 |
+
"</s>",
|
40 |
+
"<unk>"
|
41 |
+
],
|
42 |
+
"bos_token": "<s>",
|
43 |
+
"chat_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 %}",
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"eos_token": "</s>",
|
46 |
+
"max_length": 20480,
|
47 |
+
"model_input_names": [
|
48 |
+
"input_ids",
|
49 |
+
"attention_mask"
|
50 |
+
],
|
51 |
+
"model_max_length": 1000000000000000019884624838656,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"stride": 0,
|
54 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
55 |
+
"truncation_side": "right",
|
56 |
+
"truncation_strategy": "longest_first",
|
57 |
+
"unk_token": "<unk>"
|
58 |
+
}
|