Quantization made by Richard Erkhov.

youri-7b-instruction - GGUF

Model creator: https://huggingface.co/rinna/
Original model: https://huggingface.co/rinna/youri-7b-instruction/

Name	Quant method	Size
youri-7b-instruction.Q2_K.gguf	Q2_K	2.36GB
youri-7b-instruction.IQ3_XS.gguf	IQ3_XS	2.6GB
youri-7b-instruction.IQ3_S.gguf	IQ3_S	2.75GB
youri-7b-instruction.Q3_K_S.gguf	Q3_K_S	2.75GB
youri-7b-instruction.IQ3_M.gguf	IQ3_M	2.9GB
youri-7b-instruction.Q3_K.gguf	Q3_K	3.07GB
youri-7b-instruction.Q3_K_M.gguf	Q3_K_M	3.07GB
youri-7b-instruction.Q3_K_L.gguf	Q3_K_L	3.35GB
youri-7b-instruction.IQ4_XS.gguf	IQ4_XS	3.4GB
youri-7b-instruction.Q4_0.gguf	Q4_0	3.56GB
youri-7b-instruction.IQ4_NL.gguf	IQ4_NL	3.58GB
youri-7b-instruction.Q4_K_S.gguf	Q4_K_S	3.59GB
youri-7b-instruction.Q4_K.gguf	Q4_K	3.8GB
youri-7b-instruction.Q4_K_M.gguf	Q4_K_M	3.8GB
youri-7b-instruction.Q4_1.gguf	Q4_1	3.95GB
youri-7b-instruction.Q5_0.gguf	Q5_0	4.33GB
youri-7b-instruction.Q5_K_S.gguf	Q5_K_S	4.33GB
youri-7b-instruction.Q5_K.gguf	Q5_K	4.45GB
youri-7b-instruction.Q5_K_M.gguf	Q5_K_M	4.45GB
youri-7b-instruction.Q5_1.gguf	Q5_1	4.72GB
youri-7b-instruction.Q6_K.gguf	Q6_K	5.15GB
youri-7b-instruction.Q8_0.gguf	Q8_0	6.67GB

Original model description:

thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png license: llama2 language: - ja - en inference: false datasets: - databricks/databricks-dolly-15k - kunishou/databricks-dolly-15k-ja - izumi-lab/llm-japanese-dataset

`rinna/youri-7b-instruction`

Overview

The model is the instruction-tuned version of rinna/youri-7b. It adopts the Alpaca input format.

Model architecture

A 32-layer, 4096-hidden-size transformer-based language model. Refer to the llama2 paper for architecture details.
Fine-tuning

The fine-tuning data is the subset of the following datasets.
- Databricks Dolly data
- Japanese Databricks Dolly data
- FLAN Instruction Tuning data and its Japanese translation
- Izumi lab LLM Japanese dataset
  - The following sections are used
    - alt
    - aozora-txt
    - CourseraParallel
    - ParaNatCom
    - Tab-delimited_Bilingual_Sentence_Pairs
    - tanaka-corpus
    - wikinews
    - wordnet
    - yasashi-japanese
  - The remaining sections contain commonly used evaluation corpora so they are skipped to prevent data leak.
Contributors
- Tianyu Zhao
- Kei Sawada

Benchmarking

Please refer to rinna's LM benchmark page.

How to use the model

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rinna/youri-7b-instruction")
model = AutoModelForCausalLM.from_pretrained("rinna/youri-7b-instruction")

if torch.cuda.is_available():
    model = model.to("cuda")

instruction = "次の日本語を英語に翻訳してください。"
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。"
prompt = f"""
以下は、タスクを説明する指示と、文脈のある入力の組み合わせです。要求を適切に満たす応答を書きなさい。

### 指示:
{instruction}

### 入力:
{input}

### 応答:
"""
token_ids = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")

with torch.no_grad():
    output_ids = model.generate(
        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)
"""
以下は、タスクを説明する指示と、文脈のある入力の組み合わせです。要求を適切に満たす応答を書きなさい。

### 指示:
次の日本語を英語に翻訳してください。

### 入力:
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。

### 応答:
 Large language models (LLMs) are computer language models that are composed of artificial neural networks with millions to billions of parameters that are trained via self-supervised or semi-supervised learning using vast unlabeled text.</s>
"""

Tokenization

The model uses the original llama-2 tokenizer.

How to cite

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

@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},
}

License

The llama2 license