leniachat-gemma-2b-v0 / tokenizer_config.json
avacaondata's picture
Upload tokenizer
aee3fc5 verified
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<bos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"106": {
"content": "<start_of_turn>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"107": {
"content": "<end_of_turn>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"256000": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"256001": {
"content": "<user>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"256002": {
"content": "</user>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"256003": {
"content": "<system>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"256004": {
"content": "</system>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"256005": {
"content": "</assistant>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"256006": {
"content": "<input>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"256007": {
"content": "</input>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<start_of_turn>",
"<end_of_turn>"
],
"bos_token": "<bos>",
"chat_template": "{% for message in messages %}\n {% if message['role'] == 'user' %}\n {{'<user> ' + message['content'].strip() + ' </user>' }}\n {% elif message['role'] == 'system' %}\n {{'<system>\\n' + message['content'].strip() + '\\n</system>\\n\\n' }}\n {% elif message['role'] == 'assistant' %}\n {{ message['content'].strip() + ' </assistant>' + eos_token }}\n {% elif message['role'] == 'input' %}\n {{'<input> ' + message['content'] + ' </input>' }}\n {% endif %}\n{% endfor %}",
"clean_up_tokenization_spaces": false,
"do_lower_case": false,
"eos_token": "<eos>",
"legacy": null,
"model_max_length": 8192,
"pad_token": "[PAD]",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "GemmaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}