23 lines
519 B
JSON
23 lines
519 B
JSON
|
{
|
||
|
|
"tokenizer_class": "PreTrainedTokenizerFast",
|
||
|
|
"bos_token": "<bos>",
|
||
|
|
"eos_token": "<eos>",
|
||
|
|
"unk_token": "<unk>",
|
||
|
|
"pad_token": "<pad>",
|
||
|
|
"model_max_length": 512,
|
||
|
|
"vocab_size": 32000,
|
||
|
|
"clean_up_tokenization_spaces": true,
|
||
|
|
"_learnllm_meta": {
|
||
|
|
"vocab_size": 32000,
|
||
|
|
"min_frequency": 2,
|
||
|
|
"special_tokens": [
|
||
|
|
"<pad>",
|
||
|
|
"<unk>",
|
||
|
|
"<bos>",
|
||
|
|
"<eos>"
|
||
|
|
],
|
||
|
|
"sample_size_mb": 250.0,
|
||
|
|
"seed": 42,
|
||
|
|
"save_dir": "J:\\LearnLLM\\models\\tokenizer"
|
||
|
|
}
|
||
|
|
}
|