tokenizer_config.json
4 removals
Words removed | 67 |
Total words | 142 |
Words removed (%) | 47.18 |
43 lines
3 additions
Words added | 3 |
Total words | 78 |
Words added (%) | 3.85 |
42 lines
{
{
"add_bos_token": true,
"add_bos_token": true,
"add_eos_token": false,
"add_eos_token": false,
"added_tokens_decoder": {
"added_tokens_decoder": {
"0": {
"0": {
"content": "<unk>",
"content": "<unk>",
"lstrip": false,
"lstrip": false,
"normalized": true,
"normalized": false,
"rstrip": false,
"rstrip": false,
"single_word": false,
"single_word": false,
"special": true
"special": true
},
},
"1": {
"1": {
"content": "<s>",
"content": "<s>",
"lstrip": false,
"lstrip": false,
"normalized": true,
"normalized": false,
"rstrip": false,
"rstrip": false,
"single_word": false,
"single_word": false,
"special": true
"special": true
},
},
"2": {
"2": {
"content": "</s>",
"content": "</s>",
"lstrip": false,
"lstrip": false,
"normalized": true,
"normalized": false,
"rstrip": false,
"rstrip": false,
"single_word": false,
"single_word": false,
"special": true
"special": true
}
}
},
},
"additional_special_tokens": [],
"additional_special_tokens": [],
"bos_token": "<s>",
"bos_token": "<s>",
"chat_template": "chat_template\": \"{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"eos_token": "</s>",
"legacy": true,
"legacy": true,
"model_max_length": 1000000000000000019884624838656,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"pad_token": null,
"sp_model_kwargs": {},
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"unk_token": "<unk>",
"use_default_system_prompt": false
"use_default_system_prompt": false
}
}