`rinna/nekomata-14b-gguf`

Overview

The model is the GGUF version of rinna/nekomata-14b. It can be used with llama.cpp for lightweight inference.

Quantization of this model may cause stability issue in GPTQ, AWQ and GGUF q4_0. We recommend GGUF q4_K_M for 4-bit quantization.

See rinna/nekomata-14b for details about model architecture and data.

Contributors

How to use the model

See llama.cpp for more usage details.

git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp
make

MODEL_PATH=/path/to/nekomata-14b-gguf/nekomata-14b.Q4_K_M.gguf
MAX_N_TOKENS=128
PROMPT="西田幾多郎は、"

./main -m ${MODEL_PATH} -n ${MAX_N_TOKENS} -p "${PROMPT}"

Tokenization

Please refer to rinna/nekomata-14b for tokenization details.

How to cite

@misc{rinna-nekomata-14b-gguf,
    title = {rinna/nekomata-14b-gguf},
    author={Wakatsuki, Toshiaki and Zhao, Tianyu and Sawada, Kei}
    url = {https://huggingface.co/rinna/nekomata-14b-gguf},
}

@inproceedings{sawada2024release,
    title = {Release of Pre-Trained Models for the {J}apanese Language},
    author = {Sawada, Kei and Zhao, Tianyu and Shing, Makoto and Mitsui, Kentaro and Kaga, Akio and Hono, Yukiya and Wakatsuki, Toshiaki and Mitsuda, Koh},
    booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
    month = {5},
    year = {2024},
    url = {https://arxiv.org/abs/2404.01657},
}

License

Tongyi Qianwen LICENSE AGREEMENT

rinna
/

nekomata-14b-gguf