add chat template
Browse files- special_tokens_map.json +8 -21
- tokenizer.json +0 -0
- tokenizer_config.json +35 -27
special_tokens_map.json
CHANGED
@@ -1,23 +1,10 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
"
|
10 |
-
"content": "</s>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"unk_token": {
|
17 |
-
"content": "<unk>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
}
|
23 |
}
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,37 +1,45 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
"clean_up_tokenization_spaces": false,
|
13 |
-
"eos_token":
|
14 |
-
|
15 |
-
"content": "</s>",
|
16 |
-
"lstrip": false,
|
17 |
-
"normalized": false,
|
18 |
-
"rstrip": false,
|
19 |
-
"single_word": false
|
20 |
-
},
|
21 |
-
"legacy": false,
|
22 |
"model_max_length": 1000000000000000019884624838656,
|
23 |
"pad_token": null,
|
24 |
-
"padding_side": "right",
|
25 |
"sp_model_kwargs": {},
|
26 |
"spaces_between_special_tokens": false,
|
27 |
"tokenizer_class": "LlamaTokenizer",
|
28 |
-
"unk_token":
|
29 |
-
"__type": "AddedToken",
|
30 |
-
"content": "<unk>",
|
31 |
-
"lstrip": false,
|
32 |
-
"normalized": false,
|
33 |
-
"rstrip": false,
|
34 |
-
"single_word": false
|
35 |
-
},
|
36 |
"use_default_system_prompt": true
|
37 |
}
|
|
|
1 |
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
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 |
},
|
28 |
+
"additional_special_tokens": [
|
29 |
+
"<unk>",
|
30 |
+
"<s>",
|
31 |
+
"</s>"
|
32 |
+
],
|
33 |
+
"bos_token": "<s>",
|
34 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{% if message['role'] == 'system' %}{{message['content'] + ' '}}{% elif message['role'] == 'user' %}{{ 'USER: ' + message['content'] + ' '}}{% elif message['role'] == 'assistant' %}{{ 'ASSISTANT: ' + message['content'] + ' '}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'ASSISTANT: '}}{% endif %}",
|
35 |
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "</s>",
|
37 |
+
"legacy": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
"model_max_length": 1000000000000000019884624838656,
|
39 |
"pad_token": null,
|
|
|
40 |
"sp_model_kwargs": {},
|
41 |
"spaces_between_special_tokens": false,
|
42 |
"tokenizer_class": "LlamaTokenizer",
|
43 |
+
"unk_token": "<unk>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
"use_default_system_prompt": true
|
45 |
}
|