Update tokenizer_config.json
#1
by
hamishivi
- opened
- tokenizer_config.json +12 -3
tokenizer_config.json
CHANGED
@@ -2047,9 +2047,18 @@
|
|
2047 |
"rstrip": false,
|
2048 |
"single_word": false,
|
2049 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
"eos_token": "<|end_of_text|>",
|
2055 |
"model_input_names": [
|
@@ -2057,6 +2066,6 @@
|
|
2057 |
"attention_mask"
|
2058 |
],
|
2059 |
"model_max_length": 1000000000000000019884624838656,
|
2060 |
-
"
|
2061 |
-
"
|
2062 |
-
}
|
|
|
2047 |
"rstrip": false,
|
2048 |
"single_word": false,
|
2049 |
"special": true
|
2050 |
+
},
|
2051 |
+
"128256": {
|
2052 |
+
"content": "<pad>",
|
2053 |
+
"lstrip": false,
|
2054 |
+
"normalized": false,
|
2055 |
+
"rstrip": false,
|
2056 |
+
"single_word": false,
|
2057 |
+
"special": true
|
2058 |
}
|
2059 |
},
|
2060 |
"bos_token": "<|begin_of_text|>",
|
2061 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] }}\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 %}",
|
2062 |
"clean_up_tokenization_spaces": true,
|
2063 |
"eos_token": "<|end_of_text|>",
|
2064 |
"model_input_names": [
|
|
|
2066 |
"attention_mask"
|
2067 |
],
|
2068 |
"model_max_length": 1000000000000000019884624838656,
|
2069 |
+
"pad_token": "<pad>",
|
2070 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2071 |
+
}
|