thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png
license: llama3
datasets:
- mc4
- wikipedia
- EleutherAI/pile
- oscar-corpus/colossal-oscar-1.0
- cc100
language:
- ja
- en
tags:
- llama
- llama-3
inference: false
base_model: meta-llama/Meta-Llama-3-70B
Llama 3 Youko 70B (rinna/llama-3-youko-70b)
Overview
We conduct continual pre-training of meta-llama/Meta-Llama-3-70B on 5B tokens from a mixture of Japanese and English datasets. The continual pre-training significantly improves the model's performance on Japanese tasks.
The name youko comes from the Japanese word 妖狐/ようこ/Youko, which is a kind of Japanese mythical creature (妖怪/ようかい/Youkai).
| Size | Continual Pre-Training | Instruction-Tuning |
|---|---|---|
| 8B | Llama 3 Youko 8B [HF] [GPTQ] | Llama 3 Youko 8B Instruct [HF] [GPTQ] |
| 70B | Llama 3 Youko 70B [HF] [GPTQ] | Llama 3 Youko 70B Instruct [HF] [GPTQ] |
Library
The model was trained using code based on EleutherAI/gpt-neox.
Model architecture
A 80-layer, 8192-hidden-size transformer-based language model. Refer to the Llama 3 Model Card for architecture details.
Training: Built with Meta Llama 3
The model was initialized with the meta-llama/Meta-Llama-3-70B model and continually trained on around 5B tokens from a mixture of the following corpora
- Japanese CC-100
- Japanese C4
- Japanese OSCAR
- The Pile
- Wikipedia
- rinna curated Japanese dataset
Contributors
Benchmarking
Please refer to rinna's LM benchmark page.
How to use the model
import transformers
import torch
model_id = "rinna/llama-3-youko-70b"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto"
)
output = pipeline(
"西田幾多郎は、",
max_new_tokens=256,
do_sample=True
)
print(output[0]["generated_text"])
Tokenization
The model uses the original meta-llama/Meta-Llama-3-70B tokenizer.
How to cite
@misc{rinna-llama-3-youko-70b,
title = {rinna/llama-3-youko-70b},
author = {Mitsuda, Koh and Chen, Xinqi and Wakatsuki, Toshiaki and Sawada, Kei},
url = {https://huggingface.co/rinna/llama-3-youko-70b}
}
@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},
pages = {13898--13905},
url = {https://aclanthology.org/2024.lrec-main.1213},
note = {\url{https://arxiv.org/abs/2404.01657}}
}
References
@article{llama3modelcard,
title = {Llama 3 Model Card},
author = {AI@Meta},
year = {2024},
url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}
@software{gpt-neox-library,
title = {{GPT}-{N}eo{X}: Large Scale Autoregressive Language Modeling in {P}y{T}orch},
author = {Andonian, Alex and Anthony, Quentin and Biderman, Stella and Black, Sid and Gali, Preetham and Gao, Leo and Hallahan, Eric and Levy-Kramer, Josh and Leahy, Connor and Nestler, Lucas and Parker, Kip and Pieler, Michael and Purohit, Shivanshu and Songz, Tri and Phil, Wang and Weinbach, Samuel},
doi = {10.5281/zenodo.5879544},
month = {8},
year = {2021},
version = {0.0.1},
url = {https://www.github.com/eleutherai/gpt-neox}
}