Quantization made by Richard Erkhov.

nekomata-7b-instruction - GGUF

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

Name	Quant method	Size
nekomata-7b-instruction.Q2_K.gguf	Q2_K	2.84GB
nekomata-7b-instruction.IQ3_XS.gguf	IQ3_XS	3.23GB
nekomata-7b-instruction.IQ3_S.gguf	IQ3_S	3.32GB
nekomata-7b-instruction.Q3_K_S.gguf	Q3_K_S	3.32GB
nekomata-7b-instruction.IQ3_M.gguf	IQ3_M	3.61GB
nekomata-7b-instruction.Q3_K.gguf	Q3_K	3.78GB
nekomata-7b-instruction.Q3_K_M.gguf	Q3_K_M	3.78GB
nekomata-7b-instruction.Q3_K_L.gguf	Q3_K_L	4.0GB
nekomata-7b-instruction.IQ4_XS.gguf	IQ4_XS	4.02GB
nekomata-7b-instruction.Q4_0.gguf	Q4_0	4.2GB
nekomata-7b-instruction.IQ4_NL.gguf	IQ4_NL	4.22GB
nekomata-7b-instruction.Q4_K_S.gguf	Q4_K_S	4.22GB
nekomata-7b-instruction.Q4_K.gguf	Q4_K	4.56GB
nekomata-7b-instruction.Q4_K_M.gguf	Q4_K_M	4.56GB
nekomata-7b-instruction.Q4_1.gguf	Q4_1	4.62GB
nekomata-7b-instruction.Q5_0.gguf	Q5_0	5.03GB
nekomata-7b-instruction.Q5_K_S.gguf	Q5_K_S	5.03GB
nekomata-7b-instruction.Q5_K.gguf	Q5_K	5.32GB
nekomata-7b-instruction.Q5_K_M.gguf	Q5_K_M	5.32GB
nekomata-7b-instruction.Q5_1.gguf	Q5_1	5.44GB
nekomata-7b-instruction.Q6_K.gguf	Q6_K	5.91GB
nekomata-7b-instruction.Q8_0.gguf	Q8_0	7.65GB

Original model description:

thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png datasets: - databricks/databricks-dolly-15k - kunishou/databricks-dolly-15k-ja - izumi-lab/llm-japanese-dataset language: - ja - en tags: - qwen inference: false license: other license_name: tongyi-qianwen-license-agreement license_link: https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT

`rinna/nekomata-7b-instruction`

Overview

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

Model architecture

A 32-layer, 4096-hidden-size transformer-based language model. Please refer to the Qwen 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/nekomata-7b-instruction", trust_remote_code=True)

# Use GPU with bf16
# model = AutoModelForCausalLM.from_pretrained("rinna/nekomata-7b-instruction", device_map="auto", trust_remote_code=True, bf16=True)

# Use GPU with fp16
# model = AutoModelForCausalLM.from_pretrained("rinna/nekomata-7b-instruction", device_map="auto", trust_remote_code=True, fp16=True)

# Use CPU
# model = AutoModelForCausalLM.from_pretrained("rinna/nekomata-7b-instruction", device_map="cpu", trust_remote_code=True)

# Automatically select device and precision
model = AutoModelForCausalLM.from_pretrained("rinna/nekomata-7b-instruction", device_map="auto", trust_remote_code=True)

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:
 A large language model (LLM) is a computer language model composed of artificial neural networks with many parameters (from tens of millions to billions) trained by self-supervised learning or semi-supervised learning using a large amount of unlabeled text.<|endoftext|>
"""

Tokenization

Please refer to rinna/nekomata-7b for tokenization details.

How to cite

@misc{rinna-nekomata-7b-instruction,
    title = {rinna/nekomata-7b-instruction},
    author = {Zhao, Tianyu and Sawada, Kei},
    url = {https://huggingface.co/rinna/nekomata-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},
    pages = {13898--13905},
    url = {https://aclanthology.org/2024.lrec-main.1213},
    note = {\url{https://arxiv.org/abs/2404.01657}}
}

License

Tongyi Qianwen LICENSE AGREEMENT