Update tokenizer_config.json
Browse files- tokenizer_config.json +3 -0
tokenizer_config.json
CHANGED
@@ -11,9 +11,12 @@
|
|
11 |
}
|
12 |
},
|
13 |
"bos_token": "<|endoftext|>",
|
|
|
14 |
"clean_up_tokenization_spaces": true,
|
15 |
"eos_token": "<|endoftext|>",
|
|
|
16 |
"model_max_length": 1024,
|
|
|
17 |
"tokenizer_class": "GPT2Tokenizer",
|
18 |
"unk_token": "<|endoftext|>"
|
19 |
}
|
|
|
11 |
}
|
12 |
},
|
13 |
"bos_token": "<|endoftext|>",
|
14 |
+
"chat_template": "{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}",
|
15 |
"clean_up_tokenization_spaces": true,
|
16 |
"eos_token": "<|endoftext|>",
|
17 |
+
"errors": "replace",
|
18 |
"model_max_length": 1024,
|
19 |
+
"pad_token": null,
|
20 |
"tokenizer_class": "GPT2Tokenizer",
|
21 |
"unk_token": "<|endoftext|>"
|
22 |
}
|