Commit
•
2761b29
1
Parent(s):
28aa8b7
Update tokenizer_config.json
Browse files- tokenizer_config.json +6 -1
tokenizer_config.json
CHANGED
|
@@ -25,7 +25,11 @@
|
|
| 25 |
"special": true
|
| 26 |
}
|
| 27 |
},
|
| 28 |
-
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
"bos_token": "<s>",
|
| 30 |
"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 %}",
|
| 31 |
"clean_up_tokenization_spaces": false,
|
|
@@ -36,6 +40,7 @@
|
|
| 36 |
"sp_model_kwargs": {},
|
| 37 |
"spaces_between_special_tokens": false,
|
| 38 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 39 |
"unk_token": "<unk>",
|
| 40 |
"use_default_system_prompt": true
|
| 41 |
}
|
|
|
|
| 25 |
"special": true
|
| 26 |
}
|
| 27 |
},
|
| 28 |
+
"additional_special_tokens": [
|
| 29 |
+
"<unk>",
|
| 30 |
+
"<s>",
|
| 31 |
+
"</s>"
|
| 32 |
+
],
|
| 33 |
"bos_token": "<s>",
|
| 34 |
"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 %}",
|
| 35 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 40 |
"sp_model_kwargs": {},
|
| 41 |
"spaces_between_special_tokens": false,
|
| 42 |
"tokenizer_class": "LlamaTokenizer",
|
| 43 |
+
"truncation_side": "left",
|
| 44 |
"unk_token": "<unk>",
|
| 45 |
"use_default_system_prompt": true
|
| 46 |
}
|