This is a
big-endian version of
TinyLlama-1.1B-Chat-v1.0 in GGUF format, optimized for
IBM AIX on POWER architecture.
This model is designed for use with
llama-aix, a port of llama.cpp for IBM AIX.
1# Download model
2wget https://huggingface.co/librepower/tinyllama-1.1b-chat-be/resolve/main/tinyllama-1.1b-q4_k_m-be.gguf
3
4# Run inference on AIX
5./llama-simple -m tinyllama-1.1b-q4_k_m-be.gguf -n 128 -p "Hello, world!"
IBM Power Systems use big-endian byte order, while most modern systems use little-endian. This model has been converted using llama.cpp's endianness conversion tool to run natively on AIX without runtime conversion overhead.
LibrePower brings modern AI and open-source tools to IBM Power Systems, extending the life and capabilities of enterprise infrastructure.
Original model by Zhang et al. (TinyLlama team):
1@article{tinyllama,
2 title={TinyLlama: An Open-Source Small Language Model},
3 author={Zhang, Peiyuan and Guangtao, Zeng and Wang, Tianduo and Lu, Wei},
4 journal={arXiv preprint arXiv:2401.02385},
5 year={2024}
6}
