You can deploy this model and start earning money today!

RichardErkhov/
rinna_-_llama-3-youko-70b-gguf

Name: rinna_-_llama-3-youko-70b-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3-youko-70b - GGUF

Model creator: https://huggingface.co/rinna/
Original model: https://huggingface.co/rinna/llama-3-youko-70b/

Name	Quant method	Size
llama-3-youko-70b.Q2_K.gguf	Q2_K	24.56GB
llama-3-youko-70b.IQ3_XS.gguf	IQ3_XS	27.29GB
llama-3-youko-70b.IQ3_S.gguf	IQ3_S	28.79GB
llama-3-youko-70b.Q3_K_S.gguf	Q3_K_S	28.79GB
llama-3-youko-70b.IQ3_M.gguf	IQ3_M	29.74GB
llama-3-youko-70b.Q3_K.gguf	Q3_K	31.91GB
llama-3-youko-70b.Q3_K_M.gguf	Q3_K_M	31.91GB
llama-3-youko-70b.Q3_K_L.gguf	Q3_K_L	34.59GB
llama-3-youko-70b.IQ4_XS.gguf	IQ4_XS	35.64GB
llama-3-youko-70b.Q4_0.gguf	Q4_0	37.22GB
llama-3-youko-70b.IQ4_NL.gguf	IQ4_NL	37.58GB
llama-3-youko-70b.Q4_K_S.gguf	Q4_K_S	37.58GB
llama-3-youko-70b.Q4_K.gguf	Q4_K	39.6GB
llama-3-youko-70b.Q4_K_M.gguf	Q4_K_M	39.6GB
llama-3-youko-70b.Q4_1.gguf	Q4_1	41.27GB
llama-3-youko-70b.Q5_0.gguf	Q5_0	45.32GB
llama-3-youko-70b.Q5_K_S.gguf	Q5_K_S	45.32GB
llama-3-youko-70b.Q5_K.gguf	Q5_K	46.52GB
llama-3-youko-70b.Q5_K_M.gguf	Q5_K_M	46.52GB
llama-3-youko-70b.Q5_1.gguf	Q5_1	49.36GB
llama-3-youko-70b.Q6_K.gguf	Q6_K	53.91GB
llama-3-youko-70b.Q8_0.gguf	Q8_0	69.83GB

Original model description:

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

python

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

bibtex

@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