miniQwen_v3 / tokenizer_config.json
chhatramani's picture
Upload trained model and tokenizer
a41c699 verified
Raw
History Blame Contribute Delete
761 Bytes
{
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": [
"<|endoftext|>",
"<|im_start|>",
"<|im_end|>",
"<|user|>",
"<|assistant|>",
"<|system|>",
"<|thinking|>",
"<|/thinking|>",
"<|legal_doc|>",
"<|/legal_doc|>",
"<|nepali|>",
"<|english|>",
"<|court_order|>",
"<|judgement|>",
"<|statute|>",
"<|contract|>",
"<|tool_call|>",
"<|/tool_call|>"
],
"is_local": false,
"local_files_only": false,
"model_max_length": 4096,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"tokenizer_class": "TokenizersBackend",
"truncation_side": "right",
"unk_token": "<unk>"
}