Files
phi4-hindi2sanskrit-anustub…/tokenizer_config.json
ModelHub XC c4d4a26854 初始化项目,由ModelHub XC社区提供模型
Model: sanganaka/phi4-hindi2sanskrit-anustubh-lora-merged-step3400
Source: Original Platform
2026-05-02 03:34:13 +08:00

15 lines
354 B
JSON

{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"is_local": false,
"model_max_length": 16384,
"pad_token": "<|dummy_87|>",
"padding_side": "left",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "�"
}