Total runs:
482.6K
Run Growth:
-72.3K
Growth Rate:
-14.98%
Sponsored by
AdsCreator.com
rinna / llama-3-youko-8b
Model's Last Updated: March 23 2025
text-generation
Introduction of llama-3-youko-8b
Model Details of llama-3-youko-8b
Llama 3 Youko 8B (rinna/llama-3-youko-8b)
Overview
We conduct continual pre-training of meta-llama/Meta-Llama-3-8B on 22B 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 32-layer, 4096-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-3-8B model and continually trained on around 22B 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-8b"
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-3-8B tokenizer.
How to cite
@misc{rinna-llama-3-youko-8b,
title = {rinna/llama-3-youko-8b},
author = {Mitsuda, Koh and Chen, Xinqi and Wakatsuki, Toshiaki and Sawada, Kei},
url = {https://huggingface.co/rinna/llama-3-youko-8b}
}
@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}
}
License
Runs of rinna llama-3-youko-8b on huggingface.co
115
Total runs
0
24-hour runs
0
3-day runs
-11
7-day runs
-29
30-day runs
More Information About llama-3-youko-8b huggingface.co Model
Url of llama-3-youko-8b
llama-3-youko-8b huggingface.co Url
Provider of llama-3-youko-8b huggingface.co
Other API from rinna
Updated:March 23 2025
Total runs:
105.0K
Run Growth:
-74.0K
Growth Rate:
-70.49%
Total runs:
54.5K
Run Growth:
16.6K
Growth Rate:
30.45%
Total runs:
28.5K
Run Growth:
20.7K
Growth Rate:
72.63%
Total runs:
9.1K
Run Growth:
-75
Growth Rate:
-0.82%
Total runs:
7.6K
Run Growth:
-959
Growth Rate:
-12.55%
Total runs:
4.4K
Run Growth:
617
Growth Rate:
14.02%
Total runs:
4.2K
Run Growth:
-161
Growth Rate:
-3.80%
Total runs:
3.4K
Run Growth:
-3.0K
Growth Rate:
-89.67%
Total runs:
2.1K
Run Growth:
495
Growth Rate:
23.62%
Total runs:
1.3K
Run Growth:
-797
Growth Rate:
-59.43%
Total runs:
826
Run Growth:
-392
Growth Rate:
-47.46%
Total runs:
703
Run Growth:
-531
Growth Rate:
-75.53%
Total runs:
588
Run Growth:
150
Growth Rate:
25.51%
Total runs:
370
Run Growth:
239
Growth Rate:
64.77%
Total runs:
338
Run Growth:
175
Growth Rate:
51.78%
Total runs:
318
Run Growth:
138
Growth Rate:
44.81%
Total runs:
296
Run Growth:
104
Growth Rate:
37.68%
Total runs:
243
Run Growth:
101
Growth Rate:
44.89%
Total runs:
236
Run Growth:
89
Growth Rate:
40.45%
Total runs:
226
Run Growth:
127
Growth Rate:
56.44%
Total runs:
218
Run Growth:
36
Growth Rate:
16.44%
Total runs:
157
Run Growth:
36
Growth Rate:
24.66%
Total runs:
154
Run Growth:
27
Growth Rate:
17.53%
Total runs:
150
Run Growth:
44
Growth Rate:
31.65%
Total runs:
121
Run Growth:
43
Growth Rate:
35.54%
Total runs:
112
Run Growth:
74
Growth Rate:
72.55%
Total runs:
94
Run Growth:
61
Growth Rate:
73.49%
Total runs:
86
Run Growth:
59
Growth Rate:
77.63%
Total runs:
85
Run Growth:
40
Growth Rate:
53.33%
Total runs:
76
Run Growth:
-22
Growth Rate:
-28.95%
Total runs:
76
Run Growth:
45
Growth Rate:
69.23%
Total runs:
76
Run Growth:
45
Growth Rate:
69.23%
Total runs:
75
Run Growth:
44
Growth Rate:
68.75%
Total runs:
75
Run Growth:
50
Growth Rate:
76.92%
Total runs:
74
Run Growth:
47
Growth Rate:
72.31%
Total runs:
73
Run Growth:
45
Growth Rate:
61.64%
Total runs:
67
Run Growth:
-90
Growth Rate:
-134.33%
Total runs:
66
Run Growth:
30
Growth Rate:
52.63%
Total runs:
63
Run Growth:
37
Growth Rate:
69.81%
Total runs:
34
Run Growth:
-2
Growth Rate:
-5.88%
Total runs:
34
Run Growth:
0
Growth Rate:
0.00%
Total runs:
28
Run Growth:
-2
Growth Rate:
-7.14%
Total runs:
21
Run Growth:
-6
Growth Rate:
-28.57%
Total runs:
7
Run Growth:
-20
Growth Rate:
-285.71%
Total runs:
2
Run Growth:
-28
Growth Rate:
-1400.00%
Total runs:
1
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%