README.md

---
thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png
license: llama2
datasets:
- mc4
- cc100
- oscar
- wikipedia
- EleutherAI/pile
language:
- ja
- en
tags:
- gptq
inference: false
base_model: rinna/youri-7b
base_model_relation: quantized
---

# `rinna/youri-7b-gptq`

![rinna-icon](./rinna.png)

# Overview
`rinna/youri-7b-gptq` is the quantized model for [`rinna/youri-7b`](https://huggingface.co/rinna/youri-7b) using AutoGPTQ. The quantized version is 4x smaller than the original model and thus requires less memory and provides faster inference.

* **Library**
    
    Refer to the [original model](https://huggingface.co/rinna/youri-7b) for library details.

* **Model architecture**

    Refer to the [original model](https://huggingface.co/rinna/youri-7b) for architecture details.

* **Continual pre-training**

    Refer to the [original model](https://huggingface.co/rinna/youri-7b) for pre-training details.

* **Contributors**
    
    - [Toshiaki Wakatsuki](https://huggingface.co/t-w)
    - [Tianyu Zhao](https://huggingface.co/tianyuz)
    - [Kei Sawada](https://huggingface.co/keisawada)

---

# Benchmarking

Please refer to [rinna's LM benchmark page](https://rinnakk.github.io/research/benchmarks/lm/index.html).
    
---

# How to use the model

~~~~python
import torch
from transformers import AutoTokenizer
from auto_gptq import AutoGPTQForCausalLM

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

text = "西田幾多郎は、"
token_ids = tokenizer.encode(text, 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,
        min_new_tokens=200,
        do_sample=True,
        temperature=1.0,
        top_p=0.95,
        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
```bibtex
@misc{rinna-youri-7b-gptq,
    title = {rinna/youri-7b-gptq},
    author = {Wakatsuki, Toshiaki and Zhao, Tianyu and Sawada, Kei},
    url = {https://huggingface.co/rinna/youri-7b-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](https://ai.meta.com/llama/license/)