Upload tokenizer
Browse files- tokenizer.json +1 -6
- tokenizer_config.json +1 -2
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 4096,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
tokenizer_config.json
CHANGED
@@ -2066,14 +2066,13 @@
|
|
2066 |
}
|
2067 |
},
|
2068 |
"bos_token": "<|begin_of_text|>",
|
2069 |
-
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
2070 |
"clean_up_tokenization_spaces": true,
|
2071 |
"eos_token": "<|end_of_text|>",
|
2072 |
"model_input_names": [
|
2073 |
"input_ids",
|
2074 |
"attention_mask"
|
2075 |
],
|
2076 |
-
"model_max_length":
|
2077 |
"pad_token": "[PAD]",
|
2078 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2079 |
}
|
|
|
2066 |
}
|
2067 |
},
|
2068 |
"bos_token": "<|begin_of_text|>",
|
|
|
2069 |
"clean_up_tokenization_spaces": true,
|
2070 |
"eos_token": "<|end_of_text|>",
|
2071 |
"model_input_names": [
|
2072 |
"input_ids",
|
2073 |
"attention_mask"
|
2074 |
],
|
2075 |
+
"model_max_length": 1000000000000000019884624838656,
|
2076 |
"pad_token": "[PAD]",
|
2077 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2078 |
}
|