RichardErkhov/elyza_-_Llama-3-ELYZA-JP-8B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3-ELYZA-JP-8B - GGUF

• Model creator: https://huggingface.co/elyza/
• Original model: https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B/

Original model description:

• ja
• en

Llama-3-ELYZA-JP-8B

!Llama-3-ELYZA-JP-8B-image

Model Description

Llama-3-ELYZA-JP-8B is a large language model trained by ELYZA, Inc.
Based on meta-llama/Meta-Llama-3-8B-Instruct, it has been enhanced for Japanese usage through additional pre-training and instruction tuning. (Built with Meta Llama3)

For more details, please refer to our blog post.

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

DEFAULTSYSTEMPROMPT = "あなたは誠実で優秀な日本人のアシスタントです。特に指示が無い場合は、常に日本語で回答してください。"
text = "仕事の熱意を取り戻すためのアイデアを5つ挙げてください。"

model_name = "elyza/Llama-3-ELYZA-JP-8B"

tokenizer = AutoTokenizer.frompretrained(modelname)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto",
)
model.eval()

messages = [
    {"role": "system", "content": DEFAULTSYSTEMPROMPT},
    {"role": "user", "content": text},
]
prompt = tokenizer.applychattemplate(
    messages,
    tokenize=False,
    addgenerationprompt=True
)
token_ids = tokenizer.encode(
    prompt, addspecialtokens=False, return_tensors="pt"
)

with torch.no_grad():
    output_ids = model.generate(
        token_ids.to(model.device),
        maxnewtokens=1200,
        do_sample=True,
        temperature=0.6,
        top_p=0.9,
    )
output = tokenizer.decode(
    outputids.tolist()[0][tokenids.size(1):], skipspecialtokens=True
)
print(output)

Developers

Listed in alphabetical order.

• Masato Hirakawa
• Shintaro Horie
• Tomoaki Nakamura
• Daisuke Oba
• Sam Passaglia
• Akira Sasaki

License

Meta Llama 3 Community License

How to Cite

@misc{elyzallama2024,
      title={elyza/Llama-3-ELYZA-JP-8B},
      url={https://huggingface.co/elyza/Llama-3-ELYZA-JP-8B},
      author={Masato Hirakawa and Shintaro Horie and Tomoaki Nakamura and Daisuke Oba and Sam Passaglia and Akira Sasaki},
      year={2024},
}

Citations

@article{llama3modelcard,
    title={Llama 3 Model Card},
    author={AI@Meta},
    year={2024},
    url = {https://github.com/meta-llama/llama3/blob/main/MODEL_CARD.md}
}