Llama 3 Youko 8B Instruct GPTQ (rinna/llama-3-youko-8b-instruct-gptq)

👁 rinna-icon

Overview

rinna/llama-3-youko-8b-instruct-gptq is the quantized model for rinna/llama-3-youko-8b-instruct using AutoGPTQ. The quantized version is 4x smaller than the original model and thus requires less memory and provides faster inference.

• Training: Built with Meta Llama 3

  See rinna/llama-3-youko-8b-instruct for details about model architecture and data.

• Contributors

  • Toshiaki Wakatsuki
  • Xinqi Chen
  • Koh Mitsuda
  • Kei Sawada

• Release date

  July 25, 2024

---

Benchmarking

Please refer to rinna's LM benchmark page (Sheet 20240725).

---

How to use the model

We found this instruction-tuned model tends to generate repeated text more often than its base counterpart, and thus we set repetition_penalty=1.1 for better generation performance. The same repetition penalty was applied to the instruction-tuned model in the aforementioned evaluation experiments.

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "rinna/llama-3-youko-8b-instruct-gptq"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
 model_id,
 device_map="auto",
)

messages = [
 {"role": "system", "content": "あなたは誠実で優秀なアシスタントです。どうか、簡潔かつ正直に答えてください。"},
 {"role": "user", "content": "西田幾多郎とはどんな人物ですか？"},
]

input_ids = tokenizer.apply_chat_template(
 messages,
 add_generation_prompt=True,
 return_tensors="pt"
).to(model.device)

terminators = [
 tokenizer.convert_tokens_to_ids("<|end_of_text|>"),
 tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = model.generate(
 input_ids,
 max_new_tokens=512,
 eos_token_id=terminators,
 do_sample=True,
 temperature=0.6,
 top_p=0.9,
 repetition_penalty=1.1,
)

response = outputs[0][input_ids.shape[-1]:]
response = tokenizer.decode(response, skip_special_tokens=True)
print(response)

---

Tokenization

The model uses the original meta-llama/Meta-Llama-3-8B-Instruct tokenizer.

---

How to cite

@misc{rinna-llama-3-youko-8b-instruct-gptq,
 title = {rinna/llama-3-youko-8b-instruct-gptq},
 author = {Wakatsuki, Toshiaki and Chen, Xinqi and Mitsuda, Koh and Sawada, Kei},
 url = {https://huggingface.co/rinna/llama-3-youko-8b-instruct-gptq}
}

@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}
}

@article{frantar2022gptq,
 title = {{GPTQ}: Accurate Post-training Compression for Generative Pretrained Transformers},
 author = {Frantar, Elias and Ashkboos, Saleh and Hoefler, Torsten and Alistarh, Dan},
 year = {2022},
 url = {https://arxiv.org/abs/2210.17323}
}

---

License

Meta Llama 3 Community License

Base model

rinna/llama-3-youko-8b-instruct

(8)

The youko model series are based on the llama-3 series and have been continually pre-trained on Japanese-specific corpora. • 9 items • Updated Aug 26, 2025 • 1