Jalwa-latest-run-pretrain-10k / tokenizer_config.json
fhai50032's picture
Upload folder using huggingface_hub
eb88aa3 verified
{
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4709": {
"content": "user",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"27673": {
"content": "system",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"81912": {
"content": "<think>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"81913": {
"content": "</think>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"81914": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"81915": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"81916": {
"content": "assistant",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"81917": {
"content": "BiBo",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"81918": {
"content": "aloobun",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"81919": {
"content": "LowIQGenAI",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 2048,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "PreTrainedTokenizer"
}