filipealmeida
commited on
Commit
·
3fd2e9f
1
Parent(s):
f507d69
Upload 2 files
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +8 -30
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -5,7 +5,7 @@
|
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
7 |
"lstrip": false,
|
8 |
-
"normalized":
|
9 |
"rstrip": false,
|
10 |
"single_word": false,
|
11 |
"special": true
|
@@ -13,7 +13,7 @@
|
|
13 |
"1": {
|
14 |
"content": "<s>",
|
15 |
"lstrip": false,
|
16 |
-
"normalized":
|
17 |
"rstrip": false,
|
18 |
"single_word": false,
|
19 |
"special": true
|
@@ -21,45 +21,23 @@
|
|
21 |
"2": {
|
22 |
"content": "</s>",
|
23 |
"lstrip": false,
|
24 |
-
"normalized":
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
28 |
}
|
29 |
},
|
30 |
"additional_special_tokens": [],
|
31 |
-
"bos_token":
|
32 |
-
|
33 |
-
"content": "<s>",
|
34 |
-
"lstrip": false,
|
35 |
-
"normalized": true,
|
36 |
-
"rstrip": false,
|
37 |
-
"single_word": false
|
38 |
-
},
|
39 |
"clean_up_tokenization_spaces": false,
|
40 |
-
"eos_token":
|
41 |
-
"__type": "AddedToken",
|
42 |
-
"content": "</s>",
|
43 |
-
"lstrip": false,
|
44 |
-
"normalized": true,
|
45 |
-
"rstrip": false,
|
46 |
-
"single_word": false
|
47 |
-
},
|
48 |
"legacy": true,
|
49 |
"model_max_length": 1000000000000000019884624838656,
|
50 |
"pad_token": null,
|
51 |
"sp_model_kwargs": {},
|
52 |
"spaces_between_special_tokens": false,
|
53 |
"tokenizer_class": "LlamaTokenizer",
|
54 |
-
"
|
55 |
-
"
|
56 |
-
"__type": "AddedToken",
|
57 |
-
"content": "<unk>",
|
58 |
-
"lstrip": false,
|
59 |
-
"normalized": true,
|
60 |
-
"rstrip": false,
|
61 |
-
"single_word": false
|
62 |
-
},
|
63 |
-
"use_default_system_prompt": true,
|
64 |
-
"use_fast": true
|
65 |
}
|
|
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
7 |
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
"rstrip": false,
|
10 |
"single_word": false,
|
11 |
"special": true
|
|
|
13 |
"1": {
|
14 |
"content": "<s>",
|
15 |
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
"rstrip": false,
|
18 |
"single_word": false,
|
19 |
"special": true
|
|
|
21 |
"2": {
|
22 |
"content": "</s>",
|
23 |
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
28 |
}
|
29 |
},
|
30 |
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"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 %}",
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
"legacy": true,
|
36 |
"model_max_length": 1000000000000000019884624838656,
|
37 |
"pad_token": null,
|
38 |
"sp_model_kwargs": {},
|
39 |
"spaces_between_special_tokens": false,
|
40 |
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
}
|