sql-whisper-yi-from-checkpoint / tokenizer_config.json
suptejas's picture
(Trained with Unsloth)
f3915de verified
{
"add_bos_token": false,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<|startoftext|>",
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
"clean_up_tokenization_spaces": false,
"cls_token": null,
"eos_token": "<|im_end|>",
"legacy": false,
"mask_token": null,
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 4096,
"pad_token": "<unk>",
"padding_side": "left",
"sep_token": null,
"split_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"truncation_side": "right",
"unk_token": "<unk>",
"use_default_system_prompt": false
}