Fix dead split parameter in PackedStreamingDataset._load_dataset

Add Code CPT pipeline for injecting Python code capability

Remove unused tokenizer training code (train_bpe, load_sentencepiece, load_trained_hf)

Use LLaMA 2 pretrained tokenizer and remove tokenizer_mode option

Fix BPE tokenizer ByteLevel decoder and update evaluation notebook

docs: translate all Korean comments and docstrings to English

refactor(data): replace per-worker seed strategy with full sharding in IterableDataset

Initial commit: LLM-1B-Lab project setup