TinyZephyr / tokenizer_config.json
QuantaSparkLabs's picture
Fixed vocab mismatch and resized embeddings
bb329f2 verified
Raw
History Blame Contribute Delete
374 Bytes
{
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"is_local": false,
"local_files_only": false,
"max_length": 32,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|pad|>",
"stride": 0,
"tokenizer_class": "TokenizersBackend",
"truncation_side": "right",
"truncation_strategy": "longest_first"
}