OPI-PG/Qra-13b

OPI-PG/Qra-13b is a 13 billion parameter causal language model developed by the National Information Processing Institute (OPI) and Gdańsk University of Technology (PG). Adapted from Llama 2, it was further trained on a 90 billion token Polish text corpus, making it highly optimized for Polish language understanding and generation. This foundation model is designed for further fine-tuning for specific downstream tasks, excelling in perplexity benchmarks on Polish texts.