Vjeong
/

LLM-1B-Lab

Model card Files Files and versions

LLM-1B-Lab / llm_lab /data /dataset.py

Commit History

Fix dead split parameter in PackedStreamingDataset._load_dataset

0cd5689

Vjeong Claude Sonnet 4.6 commited on 1 day ago

Add Code CPT pipeline for injecting Python code capability

a424729

Vjeong Claude Opus 4.6 commited on 8 days ago

docs: translate all Korean comments and docstrings to English

858e8b2

Vjeong Claude Sonnet 4.6 commited on Feb 27

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

8a39fec

Vjeong Claude Sonnet 4.6 commited on Feb 21

Initial commit: LLM-1B-Lab project setup

8a58ffe

Vjeong Claude Opus 4.6 commited on Feb 11