Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +23 -0
tokenizer_config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {},
|
3 |
+
"additional_special_tokens": [
|
4 |
+
"<|startoftext|>",
|
5 |
+
"<|extra_0|>",
|
6 |
+
"<|extra_4|>",
|
7 |
+
"<|extra_5|>",
|
8 |
+
"<|eos|>"
|
9 |
+
],
|
10 |
+
"auto_map": {
|
11 |
+
"AutoTokenizer": [
|
12 |
+
"tokenization_hy.HYTokenizer",
|
13 |
+
null
|
14 |
+
]
|
15 |
+
},
|
16 |
+
"bos_token": "<|startoftext|>",
|
17 |
+
"chat_template": "{% set context = {'has_head': true} %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = message['content'] %}{% if loop.index0 == 0 %}{% if content == '' %}{% set _ = context.update({'has_head': false}) %}{% else %}{% set content = '<|startoftext|>' + content + '<|extra_4|>' %}{% endif %}{% endif %}{% if message['role'] == 'user' %}{% if loop.index0 == 1 and not context.has_head %}{% set content = '<|startoftext|>' + content %}{% endif %}{% if loop.index0 == 1 and context.has_head %}{% set content = content + '<|extra_0|>' %}{% else %}{% set content = '<|startoftext|>' + content + '<|extra_0|>' %}{% endif %}{% elif message['role'] == 'assistant' %}{% set content = content + '<|eos|>' %}{% endif %}{{ content }}{% endfor %}",
|
18 |
+
"clean_up_tokenization_spaces": true,
|
19 |
+
"eos_token": "<|endoftext|>",
|
20 |
+
"model_max_length": 1048576,
|
21 |
+
"pad_token": "<|pad|>",
|
22 |
+
"tokenizer_class": "HYTokenizer"
|
23 |
+
}
|