Upload tokenizer
#5
by
WesleySantos
- opened
- tokenizer.json +0 -0
- tokenizer_config.json +25 -34
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,41 +1,32 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"1": {
|
12 |
-
"content": "<s>",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": true,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"2": {
|
20 |
-
"content": "</s>",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": true,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
}
|
27 |
},
|
28 |
-
"additional_special_tokens": [],
|
29 |
-
"bos_token": "<s>",
|
30 |
-
"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 %}",
|
31 |
"clean_up_tokenization_spaces": false,
|
32 |
-
"eos_token":
|
33 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
"model_max_length": 1000000000000000019884624838656,
|
35 |
-
"pad_token":
|
36 |
"sp_model_kwargs": {},
|
37 |
-
"spaces_between_special_tokens": false,
|
38 |
"tokenizer_class": "LlamaTokenizer",
|
39 |
-
"unk_token":
|
40 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
41 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"__type": "AddedToken",
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
},
|
|
|
|
|
|
|
10 |
"clean_up_tokenization_spaces": false,
|
11 |
+
"eos_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "</s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"legacy": false,
|
20 |
"model_max_length": 1000000000000000019884624838656,
|
21 |
+
"pad_token": null,
|
22 |
"sp_model_kwargs": {},
|
|
|
23 |
"tokenizer_class": "LlamaTokenizer",
|
24 |
+
"unk_token": {
|
25 |
+
"__type": "AddedToken",
|
26 |
+
"content": "<unk>",
|
27 |
+
"lstrip": false,
|
28 |
+
"normalized": true,
|
29 |
+
"rstrip": false,
|
30 |
+
"single_word": false
|
31 |
+
}
|
32 |
}
|