sotto-cleanup-lfm25-350m-mlx-5bit / tokenizer_config.json
juanquivilla's picture
v36: full-FT GRPO with substantive-deletion-aware reward — filler-free 96.9%, sub-del-15-long 0.64%
74443d8 verified
raw
history blame
582 Bytes
{
"backend": "tokenizers",
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"extra_special_tokens": [],
"is_local": true,
"legacy": false,
"local_files_only": false,
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|pad|>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "TokenizersBackend",
"tool_parser_type": "pythonic",
"use_default_system_prompt": false,
"use_fast": true
}