rinna/llama-3-youko-8b-gptq is the quantized model for
rinna/llama-3-youko-8b using
AutoGPTQ. The quantized version is 4x smaller than the original model and thus requires less memory and provides faster inference.
-
Training: Built with Meta Llama 3
See
rinna/llama-3-youko-8b for details about model architecture and data.
-
Contributors
-
Release date
July 25, 2024
1import transformers
2import torch
3
4model_id = "rinna/llama-3-youko-8b-gptq"
5pipeline = transformers.pipeline(
6 "text-generation",
7 model=model_id,
8 device_map="auto"
9)
10output = pipeline(
11 "西田幾多郎は、",
12 max_new_tokens=256,
13 do_sample=True
14)
15print(output[0]["generated_text"])
The model uses the original
meta-llama/Meta-Llama-3-8B tokenizer.
1@misc{rinna-llama-3-youko-8b-gptq,
2 title = {rinna/llama-3-youko-8b-gptq},
3 author = {Wakatsuki, Toshiaki and Mitsuda, Koh and Chen, Xinqi and Sawada, Kei},
4 url = {https://huggingface.co/rinna/llama-3-youko-8b-gptq}
5}
6
7@inproceedings{sawada2024release,
8 title = {Release of Pre-Trained Models for the {J}apanese Language},
9 author = {Sawada, Kei and Zhao, Tianyu and Shing, Makoto and Mitsui, Kentaro and Kaga, Akio and Hono, Yukiya and Wakatsuki, Toshiaki and Mitsuda, Koh},
10 booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
11 month = {5},
12 year = {2024},
13 pages = {13898--13905},
14 url = {https://aclanthology.org/2024.lrec-main.1213},
15 note = {\url{https://arxiv.org/abs/2404.01657}}
16}
1@article{llama3modelcard,
2 title = {Llama 3 Model Card},
3 author = {AI@Meta},
4 year = {2024},
5 url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
6}
7
8@article{frantar2022gptq,
9 title = {{GPTQ}: Accurate Post-training Compression for Generative Pretrained Transformers},
10 author = {Frantar, Elias and Ashkboos, Saleh and Hoefler, Torsten and Alistarh, Dan},
11 year = {2022},
12 url = {https://arxiv.org/abs/2210.17323}
13}
