Update tokenizer
Browse files- tokenizer_config.json +1 -4
tokenizer_config.json
CHANGED
|
@@ -45,13 +45,10 @@
|
|
| 45 |
"bos_token": "<s>",
|
| 46 |
"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 %}",
|
| 47 |
"clean_up_tokenization_spaces": true,
|
| 48 |
-
"cls_token": "<s>",
|
| 49 |
"eos_token": "</s>",
|
| 50 |
"errors": "replace",
|
| 51 |
-
"
|
| 52 |
-
"model_max_length": 512,
|
| 53 |
"pad_token": "<pad>",
|
| 54 |
-
"sep_token": "</s>",
|
| 55 |
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
"trim_offsets": true,
|
| 57 |
"unk_token": "<unk>"
|
|
|
|
| 45 |
"bos_token": "<s>",
|
| 46 |
"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 %}",
|
| 47 |
"clean_up_tokenization_spaces": true,
|
|
|
|
| 48 |
"eos_token": "</s>",
|
| 49 |
"errors": "replace",
|
| 50 |
+
"model_max_length": 2048,
|
|
|
|
| 51 |
"pad_token": "<pad>",
|
|
|
|
| 52 |
"tokenizer_class": "RobertaTokenizer",
|
| 53 |
"trim_offsets": true,
|
| 54 |
"unk_token": "<unk>"
|