xiamengzhou
commited on
Commit
•
5a1f087
1
Parent(s):
5730581
update
Browse files- special_tokens_map.json +1 -0
- tokenizer.json +0 -1
- tokenizer_config.json +4 -4
special_tokens_map.json
CHANGED
@@ -13,6 +13,7 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
16 |
"unk_token": {
|
17 |
"content": "<unk>",
|
18 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "</s>",
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -134,7 +134,6 @@
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
137 |
-
"ignore_merges": false,
|
138 |
"vocab": {
|
139 |
"<unk>": 0,
|
140 |
"<s>": 1,
|
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
|
|
137 |
"vocab": {
|
138 |
"<unk>": 0,
|
139 |
"<s>": 1,
|
tokenizer_config.json
CHANGED
@@ -29,15 +29,15 @@
|
|
29 |
},
|
30 |
"additional_special_tokens": [],
|
31 |
"bos_token": "<s>",
|
32 |
-
"chat_template": "{
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
"eos_token": "</s>",
|
35 |
"legacy": true,
|
36 |
-
"model_max_length":
|
37 |
-
"pad_token":
|
38 |
"sp_model_kwargs": {},
|
39 |
"spaces_between_special_tokens": false,
|
40 |
"tokenizer_class": "LlamaTokenizer",
|
41 |
"unk_token": "<unk>",
|
42 |
"use_default_system_prompt": false
|
43 |
-
}
|
|
|
29 |
},
|
30 |
"additional_special_tokens": [],
|
31 |
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'].strip() + '\n\n' %}{% else %}{% set loop_messages = messages %}{% set system_message = '' %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{% set content = system_message + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
"eos_token": "</s>",
|
35 |
"legacy": true,
|
36 |
+
"model_max_length": 2048,
|
37 |
+
"pad_token": "</s>",
|
38 |
"sp_model_kwargs": {},
|
39 |
"spaces_between_special_tokens": false,
|
40 |
"tokenizer_class": "LlamaTokenizer",
|
41 |
"unk_token": "<unk>",
|
42 |
"use_default_system_prompt": false
|
43 |
+
}
|