chatglm3-6b-medqa-version0 / tokenizer_config.json
SilasK's picture
Training in progress, epoch 0
0bd0262 verified
{
"added_tokens_decoder": {
"64790": {
"content": "[gMASK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"64792": {
"content": "sop",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"64795": {
"content": "<|user|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"64796": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64797": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_end|>",
"<|im_start|>"
],
"auto_map": {
"AutoTokenizer": [
"THUDM/chatglm3-6b--tokenization_chatglm.ChatGLMTokenizer",
null
]
},
"bos_token": "<|im_start|>",
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"do_lower_case": false,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<unk>",
"padding_side": "left",
"remove_space": false,
"tokenizer_class": "ChatGLMTokenizer",
"unk_token": "<unk>"
}