turkish-gpt2-large-750m-instruct-v0.1 / tokenizer_config.json
tkesgin's picture
Update tokenizer_config.json (#10)
f0cafc3 verified
raw
history blame
1.12 kB
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50257": {
"content": "<|stop|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<|endoftext|>",
"chat_template": "{% for message in (messages[-4:] if messages|length >= 4 and messages[-4].role == 'user' else messages[-3:] if messages|length > 3 else messages) %}{% if message.role == 'user' %}### Kullanıcı:\n{{ message.content }}\n{% elif message.role == 'assistant' %}### Asistan:\n{{ message.content }}\n{% endif %}{% endfor %}{% if messages[-1]['role'] == 'user' %}### Asistan:\n{% endif %}",
"clean_up_tokenization_spaces": true,
"eos_token": "<|stop|>",
"errors": "replace",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}