biomedical_llama_1B / tokenizer_config.json
guilhermenf's picture
Training in progress, step 39
be76a6d verified
{
"backend": "tokenizers",
"bos_token": "<|begin_of_text|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|eot_id|>",
"is_local": false,
"max_length": 4096,
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 4096,
"pad_token": "<|eot_id|>",
"padding_side": "left",
"stride": 0,
"tokenizer_class": "TokenizersBackend",
"truncation_side": "right",
"truncation_strategy": "longest_first"
}