codestral-learn-60-epoch-4-f-awq / tokenizer_config.json
dan-kwiat's picture
Upload folder using huggingface_hub
a21a211 verified
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[INST]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"4": {
"content": "[/INST]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"10": {
"content": "[IMG]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"11": {
"content": "[PREFIX]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"12": {
"content": "[MIDDLE]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"13": {
"content": "[SUFFIX]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<s>",
"chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% if messages[1]['role'] == 'user' %}{{ '[INST] ' + messages[0]['content'] + ' ' + messages[1]['content'] + ' [/INST]' }}{% set loop_messages = messages[2:] %}{% else %}{{ '[INST] ' + messages[0]['content'] + ' [/INST]' }}{% set loop_messages = messages[1:] %}{% endif %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% 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,
"eos_token": "</s>",
"legacy": true,
"model_max_length": 32768,
"pad_token": "<unk>",
"padding_side": "left",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}