Instructions to use RichardErkhov/rinna_-_llama-3-youko-8b-4bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/rinna_-_llama-3-youko-8b-4bits with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="RichardErkhov/rinna_-_llama-3-youko-8b-4bits")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RichardErkhov/rinna_-_llama-3-youko-8b-4bits")
model = AutoModelForCausalLM.from_pretrained("RichardErkhov/rinna_-_llama-3-youko-8b-4bits")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RichardErkhov/rinna_-_llama-3-youko-8b-4bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RichardErkhov/rinna_-_llama-3-youko-8b-4bits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RichardErkhov/rinna_-_llama-3-youko-8b-4bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RichardErkhov/rinna_-_llama-3-youko-8b-4bits

SGLang

How to use RichardErkhov/rinna_-_llama-3-youko-8b-4bits with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "RichardErkhov/rinna_-_llama-3-youko-8b-4bits" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RichardErkhov/rinna_-_llama-3-youko-8b-4bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "RichardErkhov/rinna_-_llama-3-youko-8b-4bits" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RichardErkhov/rinna_-_llama-3-youko-8b-4bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RichardErkhov/rinna_-_llama-3-youko-8b-4bits with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/rinna_-_llama-3-youko-8b-4bits
```

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3-youko-8b - bnb 4bits

Model creator: https://huggingface.co/rinna/
Original model: https://huggingface.co/rinna/llama-3-youko-8b/

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 inference: false

`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).

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
- Koh Mitsuda
- Kei Sawada

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)

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 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},
    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-NeoX: Large Scale Autoregressive Language Modeling in PyTorch}},
    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},
}