nyayalm-tokenizer-test / tokenizer_config.json
chhatramani's picture
Upload NyayaLM tokenizer folder
ba11d88 verified
Raw
History Blame Contribute Delete
1.86 kB
{
"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|>",
"<|reserved_special_token_0|>",
"<|reserved_special_token_1|>",
"<|reserved_special_token_2|>",
"<|reserved_special_token_3|>",
"<|reserved_special_token_4|>",
"<|reserved_special_token_5|>",
"<|reserved_special_token_6|>",
"<|reserved_special_token_7|>",
"<|reserved_special_token_8|>",
"<|reserved_special_token_9|>",
"<|reserved_special_token_10|>",
"<|reserved_special_token_11|>",
"<|reserved_special_token_12|>",
"<|reserved_special_token_13|>",
"<|reserved_special_token_14|>",
"<|reserved_special_token_15|>",
"<|reserved_special_token_16|>",
"<|reserved_special_token_17|>",
"<|reserved_special_token_18|>",
"<|reserved_special_token_19|>",
"<|reserved_special_token_20|>",
"<|reserved_special_token_21|>",
"<|reserved_special_token_22|>",
"<|reserved_special_token_23|>",
"<|reserved_special_token_24|>",
"<|reserved_special_token_25|>",
"<|reserved_special_token_26|>",
"<|reserved_special_token_27|>",
"<|reserved_special_token_28|>",
"<|reserved_special_token_29|>",
"<|reserved_special_token_30|>",
"<|reserved_special_token_31|>"
],
"model_max_length": 4096,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"tokenizer_class": "TokenizersBackend",
"truncation_side": "right",
"unk_token": "<unk>"
}