Rakutenai 7B Chat

🚀 RakutenAI-7B-chat

RakutenAI-7B-chat is a high - performance language model that excels in both Japanese and English, offering advanced language understanding and generation capabilities.

🚀 Quick Start

The following code examples demonstrate how to use the RakutenAI-7B-chat model:

Basic Usage

# With RakutenAI-7B-Chat's custom chat template.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "Rakuten/RakutenAI-7B-chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype="auto", device_map="auto")
model.eval()

chat = [
	
	{"role": "system", "content": "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions."},
	{"role": "user", "content": "How to make an authentic Spanish Omelette?"},
]

input_ids = tokenizer.apply_chat_template(chat, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(device=model.device)
tokens = model.generate(
    input_ids,
    max_length=4096,
    do_sample=False,
    num_beams=1,
    pad_token_id=tokenizer.eos_token_id,
)
out = tokenizer.decode(tokens[0][len(input_ids[0]):], skip_special_tokens=True)
print("ASSISTANT:\n" + out)
print()


# Without using custom chat template.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "Rakuten/RakutenAI-7B-chat"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype="auto", device_map="auto")
model.eval()

requests = [
    "「馬が合う」はどう言う意味ですか",
    "How to make an authentic Spanish Omelette?",
]

system_message = "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {user_input} ASSISTANT:"

for req in requests:
    input_req = system_message.format(user_input=req)
    input_ids = tokenizer.encode(input_req, return_tensors="pt").to(device=model.device)
    tokens = model.generate(
        input_ids,
        max_new_tokens=1024,
        do_sample=True,
        pad_token_id=tokenizer.eos_token_id,
    )
    out = tokenizer.decode(tokens[0][len(input_ids[0]):], skip_special_tokens=True)
    print("USER:\n" + req)
    print("ASSISTANT:\n" + out)
    print()
    print()

✨ Features

• High - performance in Japanese and English: RakutenAI-7B achieves the best scores on Japanese language understanding benchmarks and maintains competitive performance on English test sets among similar models.
• Leverage Mistral architecture: Based on the Mistral-7B-v0.1 pre - trained checkpoint, it successfully retrofits pre - trained model weights.
• Extended vocabulary: Extend Mistral's vocabulary from 32k to 48k to offer a better character - per - token rate for Japanese.

📚 Documentation

Model Description

RakutenAI-7B is a systematic initiative that brings the latest technologies to the world of Japanese LLMs. It achieves the best scores on the Japanese language understanding benchmarks while maintaining a competitive performance on the English test sets among similar models such as OpenCalm, Elyza, Youri, Nekomata and Swallow. It leverages the Mistral model architecture and is based on Mistral-7B-v0.1 pre - trained checkpoint, exemplifying a successful retrofitting of the pre - trained model weights. Moreover, it extends Mistral's vocabulary from 32k to 48k to offer a better character - per - token rate for Japanese.

The technical report can be accessed at arXiv.

If you are looking for a foundation model, check RakutenAI-7B.

If you are looking for an instruction - tuned model, check RakutenAI-7B-instruct.

An independent evaluation by Kamata et.al. for Nejumi LLMリーダーボード Neo using a weighted average of llm - jp - eval and [Japanese MT - bench](https://github.com/Stability - AI/FastChat/tree/jp - stable/fastchat/llm_judge) also confirms the highest performance of chat/instruct versions of RakutenAI-7B among Open LLMs of similar sizes, with a score of 0.393/0.331 respectively, as of 22nd March 2024.

Model Details

Limitations and Bias

The suite of RakutenAI-7B models is capable of generating human - like text on a wide range of topics. However, like all LLMs, they have limitations and can produce biased, inaccurate, or unsafe outputs. Please exercise caution and judgement while interacting with them.

📄 License

This model is licensed under Apache License, Version 2.0.

📚 Citation

For citing our work on the suite of RakutenAI-7B models, please use:

@misc{rakutengroup2024rakutenai7b,
      title={RakutenAI-7B: Extending Large Language Models for Japanese}, 
      author={{Rakuten Group, Inc.} and Aaron Levine and Connie Huang and Chenguang Wang and Eduardo Batista and Ewa Szymanska and Hongyi Ding and Hou Wei Chou and Jean-François Pessiot and Johanes Effendi and Justin Chiu and Kai Torben Ohlhus and Karan Chopra and Keiji Shinzato and Koji Murakami and Lee Xiong and Lei Chen and Maki Kubota and Maksim Tkachenko and Miroku Lee and Naoki Takahashi and Prathyusha Jwalapuram and Ryutaro Tatsushima and Saurabh Jain and Sunil Kumar Yadav and Ting Cai and Wei-Te Chen and Yandi Xia and Yuki Nakayama and Yutaka Higashiyama},
      year={2024},
      eprint={2403.15484},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}