Upload tokenizer
Browse files- special_tokens_map.json +0 -1
- tokenizer_config.json +0 -2
special_tokens_map.json
CHANGED
@@ -1,6 +1,5 @@
|
|
1 |
{
|
2 |
"bos_token": "<|endoftext|>",
|
3 |
"eos_token": "<|endoftext|>",
|
4 |
-
"pad_token": "<|endoftext|>",
|
5 |
"unk_token": "<|endoftext|>"
|
6 |
}
|
|
|
1 |
{
|
2 |
"bos_token": "<|endoftext|>",
|
3 |
"eos_token": "<|endoftext|>",
|
|
|
4 |
"unk_token": "<|endoftext|>"
|
5 |
}
|
tokenizer_config.json
CHANGED
@@ -11,11 +11,9 @@
|
|
11 |
}
|
12 |
},
|
13 |
"bos_token": "<|endoftext|>",
|
14 |
-
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
15 |
"clean_up_tokenization_spaces": true,
|
16 |
"eos_token": "<|endoftext|>",
|
17 |
"model_max_length": 1024,
|
18 |
-
"pad_token": "<|endoftext|>",
|
19 |
"tokenizer_class": "GPT2Tokenizer",
|
20 |
"unk_token": "<|endoftext|>"
|
21 |
}
|
|
|
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 |
}
|