codebert-permissive-embed / tokenizer_config.json
malleshmadapathi's picture
Stage-2 code embedding model: permissive-only corpus, function-level contrastive tuning
c3ebc49 verified
Raw
History Blame Contribute Delete
440 Bytes
{
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"is_local": true,
"local_files_only": false,
"mask_token": "<|mask|>",
"max_length": 512,
"model_max_length": 1000000,
"pad_token": "<|pad|>",
"stride": 0,
"tokenizer_class": "TokenizersBackend",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": null
}