for file_name in ${array[@]} do python tools/preprocess_data.py \ --input /RedPajama-Data-1T-Sample/${file_name}.jsonl \ --output-prefix red_data/reapajama_${file_name} \ --tokenizer-type Llama2Tokenizer \ --tokenizer-model /Llama-2-70b-hf/tokenizer.model \ --append-eod \ -...