rinna/youri-7b-chat-gptq

Overview

rinna/youri-7b-chat-gptq is the quantized model for rinna/youri-7b-chat using AutoGPTQ. The quantized version is 4x smaller than the original model and thus requires less memory and provides faster inference.

• Model architecture

  Refer to the original model for architecture details.

• Fine-tuning

  Refer to the original model for fine-tuning details.

• Contributors

  • Toshiaki Wakatsuki
  • Tianyu Zhao
  • Kei Sawada

---

Benchmarking

Please refer to rinna's LM benchmark page.

---

How to use the model

import torch
from transformers import AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rinna/youri-7b-chat-gptq")
model = AutoGPTQForCausalLM.from_quantized("rinna/youri-7b-chat-gptq", use_safetensors=True)

instruction = "次の日本語を英語に翻訳してください。"
input = "自然言語による指示に基づきタスクが解けるよう学習させることを Instruction tuning と呼びます。"

context = [
    {
        "speaker": "設定",
        "text": instruction
    },
    {
        "speaker": "ユーザー",
        "text": input
    }
]
prompt = [
    f"{uttr['speaker']}: {uttr['text']}"
    for uttr in context
]
prompt = "\n".join(prompt)
prompt = (
    prompt
    + "\n"
    + "システム: "
)
token_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")

with torch.no_grad():
    output_ids = model.generate(
        input_ids=token_ids.to(model.device),
        max_new_tokens=200,
        do_sample=True,
        temperature=0.5,
        pad_token_id=tokenizer.pad_token_id,
        bos_token_id=tokenizer.bos_token_id,
        eos_token_id=tokenizer.eos_token_id
    )

output = tokenizer.decode(output_ids.tolist()[0])
print(output)

output = output[len(prompt):-len("</s>")].strip()
input = "大規模言語モデル（だいきぼげんごモデル、英: large language model、LLM）は、多数のパラメータ（数千万から数十億）を持つ人工ニューラルネットワークで構成されるコンピュータ言語モデルで、膨大なラベルなしテキストを使用して自己教師あり学習または半教師あり学習によって訓練が行われる。"

context.extend([
    {
        "speaker": "システム",
        "text": output
    },
    {
        "speaker": "ユーザー",
        "text": input
    }
])
prompt = [
    f"{uttr['speaker']}: {uttr['text']}"
    for uttr in context
]
prompt = "\n".join(prompt)
prompt = (
    prompt
    + "\n"
    + "システム: "
)
token_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")

with torch.no_grad():
    output_ids = model.generate(
        input_ids=token_ids.to(model.device),
        max_new_tokens=200,
        do_sample=True,
        temperature=0.5,
        pad_token_id=tokenizer.pad_token_id,
        bos_token_id=tokenizer.bos_token_id,
        eos_token_id=tokenizer.eos_token_id
    )

output = tokenizer.decode(output_ids.tolist()[0])
print(output)

---

Tokenization

The model uses the original llama-2 tokenizer.

---

How to cite

@misc{rinna-youri-7b-chat-gptq,
    title = {rinna/youri-7b-chat-gptq},
    author = {Wakatsuki, Toshiaki and Zhao, Tianyu and Sawada, Kei},
    url = {https://huggingface.co/rinna/youri-7b-chat-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}}
}

---

License

The llama2 license