30 lines
671 B
JSON
30 lines
671 B
JSON
|
{
|
||
|
|
"add_prefix_space": false,
|
||
|
|
"backend": "tokenizers",
|
||
|
|
"bos_token": "<|endoftext|>",
|
||
|
|
"eos_token": "<|endoftext|>",
|
||
|
|
"errors": "replace",
|
||
|
|
"extra_special_tokens": [
|
||
|
|
"<think>",
|
||
|
|
"</think>",
|
||
|
|
"<tool_call>",
|
||
|
|
"</tool_call>",
|
||
|
|
"<tool_response>",
|
||
|
|
"</tool_response>",
|
||
|
|
"<pad>"
|
||
|
|
],
|
||
|
|
"is_local": false,
|
||
|
|
"local_files_only": false,
|
||
|
|
"max_length": 256,
|
||
|
|
"model_max_length": 1024,
|
||
|
|
"pad_to_multiple_of": null,
|
||
|
|
"pad_token": "<pad>",
|
||
|
|
"pad_token_type_id": 0,
|
||
|
|
"padding_side": "right",
|
||
|
|
"stride": 0,
|
||
|
|
"tokenizer_class": "GPT2Tokenizer",
|
||
|
|
"truncation_side": "right",
|
||
|
|
"truncation_strategy": "longest_first",
|
||
|
|
"unk_token": "<|endoftext|>"
|
||
|
|
}
|