Name	Quant method	Size
llama-3-youko-70b-instruct.Q2_K.gguf	Q2_K	24.56GB
llama-3-youko-70b-instruct.IQ3_XS.gguf	IQ3_XS	27.29GB
llama-3-youko-70b-instruct.IQ3_S.gguf	IQ3_S	28.79GB
llama-3-youko-70b-instruct.Q3_K_S.gguf	Q3_K_S	28.79GB
llama-3-youko-70b-instruct.IQ3_M.gguf	IQ3_M	29.74GB
llama-3-youko-70b-instruct.Q3_K.gguf	Q3_K	31.91GB
llama-3-youko-70b-instruct.Q3_K_M.gguf	Q3_K_M	31.91GB
llama-3-youko-70b-instruct.Q3_K_L.gguf	Q3_K_L	34.59GB
llama-3-youko-70b-instruct.IQ4_XS.gguf	IQ4_XS	35.64GB
llama-3-youko-70b-instruct.Q4_0.gguf	Q4_0	37.22GB
llama-3-youko-70b-instruct.IQ4_NL.gguf	IQ4_NL	37.58GB
llama-3-youko-70b-instruct.Q4_K_S.gguf	Q4_K_S	37.58GB
llama-3-youko-70b-instruct.Q4_K.gguf	Q4_K	39.6GB
llama-3-youko-70b-instruct.Q4_K_M.gguf	Q4_K_M	39.6GB
llama-3-youko-70b-instruct.Q4_1.gguf	Q4_1	41.27GB
llama-3-youko-70b-instruct.Q5_0.gguf	Q5_0	45.32GB
llama-3-youko-70b-instruct.Q5_K_S.gguf	Q5_K_S	45.32GB
llama-3-youko-70b-instruct.Q5_K.gguf	Q5_K	46.52GB
llama-3-youko-70b-instruct.Q5_K_M.gguf	Q5_K_M	46.52GB
llama-3-youko-70b-instruct.Q5_1.gguf	Q5_1	49.36GB
llama-3-youko-70b-instruct.Q6_K.gguf	Q6_K	53.91GB
llama-3-youko-70b-instruct.Q8_0.gguf	Q8_0	69.83GB

Original model description:

thumbnail: https://github.com/rinnakk/japanese-pretrained-models/blob/master/rinna.png license: llama3 language:

ja
en tags:
llama
llama-3 inference: false base_model:
rinna/llama-3-youko-70b
meta-llama/Meta-Llama-3-70B
meta-llama/Meta-Llama-3-70B-Instruct base_model_relation: merge

`Llama 3 Youko 70B Instruct (rinna/llama-3-youko-70b-instruct)`

Overview

The model is the instruction-tuned version of rinna/llama-3-youko-70b, using supervised fine-tuning (SFT) and Chat Vector. It adpots the Llama-3 chat format.

Size	Continual Pre-Training	Instruction-Tuning
8B	Llama 3 Youko 8B [HF] [GPTQ]	Llama 3 Youko 8B Instruct [HF] [GPTQ]
70B	Llama 3 Youko 70B [HF] [GPTQ]	Llama 3 Youko 70B Instruct [HF] [GPTQ]

Model architecture

A 80-layer, 8192-hidden-size transformer-based language model. Refer to the Llama 3 Model Card for architecture details.
Training: Built with Meta Llama 3

Supervised fine-tuning. The supervised fine-tuning data is the following dataset.
- rinna Dataset
Model merging. The fine-tuned model (llama-3-youko-70b-sft) has been enhanced through the following chat vector addition. The chat vector was obtained by subtracting the parameter vectors of meta-llama/Meta-Llama-3-70B from those of meta-llama/Meta-Llama-3-70B-Instruct.

llama-3-youko-70b-sft + 0.5 * (meta-llama/Meta-Llama-3-70B-Instruct - meta-llama/Meta-Llama-3-70B)

Here, the embedding layer was skipped while subtracting and adding the parameter vectors.
Contributors

Benchmarking

Please refer to rinna's LM benchmark page.

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.

python

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "rinna/llama-3-youko-70b-instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    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-3-70B-Instruct tokenizer.

How to cite

bibtex

@misc{rinna-llama-3-youko-70b-instruct,
    title = {rinna/llama-3-youko-70b-instruct},
    author = {Mitsuda, Koh and Chen, Xinqi and Wakatsuki, Toshiaki and Sawada, Kei},
    url = {https://huggingface.co/rinna/llama-3-youko-70b-instruct}
}

@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

bibtex

@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{huang2023chat,
    title = {Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages},
    author = {Huang, Shih-Cheng and Li, Pin-Zu and Hsu, Yu-Chi and Chen, Kuang-Ming and Lin, Yu Tung and Hsiao, Shih-Kai and Tzong-Han Tsai, Richard and Lee, Hung-yi},
    year = {2023},
    url = {https://arxiv.org/abs/2310.04799}
}

License

Meta Llama 3 Community License

RichardErkhov/rinna_-_llama-3-youko-70b-instruct-gguf