`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
Release date

July 25, 2024

Benchmarking

Please refer to rinna's LM benchmark page (Sheet 20240725).

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.

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

@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

@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}
}