Commit
•
507254d
1
Parent(s):
e6185e1
fix: add chat template to tokenizer config
Browse files- tokenizer_config.json +9 -1
tokenizer_config.json
CHANGED
@@ -5,5 +5,13 @@
|
|
5 |
"tokenization_arcade100k.Arcade100kTokenizer",
|
6 |
null
|
7 |
]
|
8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
}
|
|
|
5 |
"tokenization_arcade100k.Arcade100kTokenizer",
|
6 |
null
|
7 |
]
|
8 |
+
},
|
9 |
+
"added_tokens_decoder": {},
|
10 |
+
"bos_token": "<|endoftext|>",
|
11 |
+
"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 %}",
|
12 |
+
"clean_up_tokenization_spaces": true,
|
13 |
+
"eos_token": "<|endoftext|>",
|
14 |
+
"errors": "replace",
|
15 |
+
"model_max_length": 4096,
|
16 |
+
"pad_token": "<|endoftext|>"
|
17 |
}
|