Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +6 -16
tokenizer_config.json
CHANGED
|
@@ -1,19 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"GPT2LMHeadModel"
|
| 4 |
-
],
|
| 5 |
-
"model_max_length": 262144,
|
| 6 |
-
"tokenizer_class": "HYTokenizer",
|
| 7 |
-
"auto_map": {
|
| 8 |
-
"AutoTokenizer": [
|
| 9 |
-
"tokenization_hy.HYTokenizer",
|
| 10 |
-
null
|
| 11 |
-
]
|
| 12 |
-
},
|
| 13 |
-
"eos_token": "<|eos|>",
|
| 14 |
"bos_token": "<|startoftext|>",
|
| 15 |
-
"
|
| 16 |
-
"
|
|
|
|
| 17 |
"pad_token": "<|pad|>",
|
| 18 |
-
"
|
| 19 |
-
}
|
|
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<|startoftext|>",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"eos_token": "<|eos|>",
|
| 5 |
+
"model_max_length": 262144,
|
| 6 |
"pad_token": "<|pad|>",
|
| 7 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 8 |
+
"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}) %}{% elif message['role'] == 'system' %}{% 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 %}"
|
| 9 |
+
}
|