Swallow MX 8x7b NVE V0.1

🚀 Swallow-MX-8x7b-NVE-v0.1

Our Swallow-MX-8x7b-NVE-v0.1 model is continuously pre - trained from Mixtral-8x7B-Instruct-v0.1, with a major addition of Japanese language data.

🚀 Quick Start

First, install additional dependencies in requirements.txt:

pip install -r requirements.txt

Use the base model

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
prompt = "東京工業大学の主なキャンパスは、"
input_ids = tokenizer.encode(
    prompt,
    add_special_tokens=False,
    return_tensors="pt"
)
tokens = model.generate(
    input_ids.to(device=model.device),
    max_new_tokens=128,
    temperature=0.99,
    top_p=0.95,
    do_sample=True,
)

out = tokenizer.decode(tokens[0], skip_special_tokens=True)
print(out)

✨ Features

• The model is pre - trained from Mixtral-8x7B-Instruct-v0.1, adding Japanese language data.
• It shows good performance in both Japanese and English tasks.

📦 Installation

First install additional dependencies in requirements.txt:

pip install -r requirements.txt

💻 Usage Examples

Basic Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
prompt = "東京工業大学の主なキャンパスは、"
input_ids = tokenizer.encode(
    prompt,
    add_special_tokens=False,
    return_tensors="pt"
)
tokens = model.generate(
    input_ids.to(device=model.device),
    max_new_tokens=128,
    temperature=0.99,
    top_p=0.95,
    do_sample=True,
)

out = tokenizer.decode(tokens[0], skip_special_tokens=True)
print(out)

📚 Documentation

Model Details

Base Model Performance

Japanese version

English version

Training Datasets

Continual Pre - Training

The following datasets were used for continual pre - training:

• [Algebraic Stack](https://huggingface.co/datasets/EleutherAI/proof - pile - 2)
• Japanese Wikipedia
• [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon - refinedweb)
• Swallow Corpus
• The Pile
• [The Vault](https://github.com/FSoft - AI4Code/TheVault)

Risks and Limitations

The models released here are still in the early stages of our research and development and have not been tuned to ensure outputs align with human intent and safety considerations.

Acknowledgements

We thank Mistral AI for releasing Mixtral-8x7B-Instruct-v0.1 under an open license for others to build on.

Our project is supported by the ABCI Large - scale Language Model Building Support Program of the National Institute of Advanced Industrial Science and Technology.

How to cite

If you find our work helpful, please feel free to cite us.

@inproceedings{Fujii:COLM2024,
   title={Continual Pre - Training for Cross - Lingual LLM Adaptation:
Enhancing Japanese Language Capabilities},
   author={Kazuki Fujii and Taishi Nakamura and Mengsay Loem and Hiroki
Iida and Masanari Ohi and Kakeru Hattori and Hirai Shota and Sakae
Mizuki and Rio Yokota and Naoaki Okazaki},
   booktitle="Proceedings of the First Conference on Language Modeling",
   series={COLM},
   pages="(to appear)",
   year="2024",
   month=oct,
   address={University of Pennsylvania, USA},
}

@inproceedings{Okazaki:COLM2024,
   title={Building a Large Japanese Web Corpus for Large Language Models},
   author={Naoaki Okazaki and Kakeru Hattori and Hirai Shota and Hiroki
Iida and Masanari Ohi and Kazuki Fujii and Taishi Nakamura and Mengsay
Loem and Rio Yokota and Sakae Mizuki},
   booktitle="Proceedings of the First Conference on Language Modeling",
   series={COLM},
   pages="(to appear)",
   year="2024",
   month=oct,
   address={University of Pennsylvania, USA},
}

📄 License

apache - 2.0

Authors

Here are the team members:

• From Okazaki Laboratory:
  • Naoaki Okazaki
  • [Sakae Mizuki](https://s - mizuki - nlp.github.io/)
  • Hiroki Iida
  • [Mengsay Loem](https://loem - ms.github.io/)
  • Shota Hirai
  • [Kakeru Hattori](https://aya - se.vercel.app/)
  • Masanari Ohi
• From YOKOTA Laboratory:
  • Rio Yokota
  • Kazuki Fujii
  • Taishi Nakamura