Swallow 70b Hf

🚀 Swallow

Our Swallow model is continuously pre - trained from the Llama 2 family, mainly with the addition of Japanese language data. The tuned versions use supervised fine - tuning (SFT). Links to other models can be found in the index.

🚀 Quick Start

This repository provides large language models developed by TokyoTech-LLM. You can read our blog post or our paper for more information.

✨ Features

• The Swallow model is based on the Llama 2 family and has been continuously pre - trained with additional Japanese language data.
• Tuned versions use supervised fine - tuning (SFT).
• It has a tokenizer with an expanded vocabulary based on Japanese data, enabling more efficient text representation and faster inference.

📦 Installation

First, install additional dependencies in requirements.txt:

pip install -r requirements.txt

💻 Usage Examples

Basic Usage

Use the instruct model

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "tokyotech-llm/Swallow-7b-instruct-hf"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, low_cpu_mem_usage=True, device_map="auto")


PROMPT_DICT = {
    "prompt_input": (
        "以下に、あるタスクを説明する指示があり、それに付随する入力が更なる文脈を提供しています。"
        "リクエストを適切に完了するための回答を記述してください。\n\n"
        "### 指示:\n{instruction}\n\n### 入力:\n{input}\n\n### 応答:"

    ),
    "prompt_no_input": (
        "以下に、あるタスクを説明する指示があります。"
        "リクエストを適切に完了するための回答を記述してください。\n\n"
        "### 指示:\n{instruction}\n\n### 応答:"
    ),
}

def create_prompt(instruction, input=None):
    """
    Generates a prompt based on the given instruction and an optional input.
    If input is provided, it uses the 'prompt_input' template from PROMPT_DICT.
    If no input is provided, it uses the 'prompt_no_input' template.

    Args:
        instruction (str): The instruction describing the task.
        input (str, optional): Additional input providing context for the task. Default is None.

    Returns:
        str: The generated prompt.
    """
    if input:
        # Use the 'prompt_input' template when additional input is provided
        return PROMPT_DICT["prompt_input"].format(instruction=instruction, input=input)
    else:
        # Use the 'prompt_no_input' template when no additional input is provided
        return PROMPT_DICT["prompt_no_input"].format(instruction=instruction)

# Example usage
instruction_example = "以下のトピックに関する詳細な情報を提供してください。"
input_example = "東京工業大学の主なキャンパスについて教えてください"
prompt = create_prompt(instruction_example, input_example)

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)

Use the base model

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "tokyotech-llm/Swallow-7b-hf"

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 Release Updates

We are excited to share the release schedule for our latest models:

• April 26, 2024: Released version 0.1 of our enhanced instruction - tuned models: Swallow-7b-instruct-v0.1, Swallow-13b-instruct-v0.1, and Swallow-70b-instruct-v0.1 as preview versions.
• March 2, 2024: Released the Swallow-7b-plus-hf, a model trained with approximately twice as many Japanese tokens as Swallow-7b-hf.
• February 4, 2024: Released the Swallow-13b-NVE-hf.
• January 26, 2024: Released the Swallow-7b-NVE-hf, Swallow-7b-NVE-instruct-hf, Swallow-70b-NVE-hf, and Swallow-70b-NVE-instruct-hf
• December 19, 2023: Released the Swallow-7b-hf, Swallow-7b-instruct-hf, Swallow-13b-hf, Swallow-13b-instruct-hf, Swallow-70b-hf, and Swallow-70b-instruct-hf.

Swallow Model Index

Swallow Model Index NVE (No Vocabulary Expansion)

Model Details

Base Model Performance

Japanese tasks

English tasks

Evaluation Benchmarks

Japanese evaluation benchmarks

We used llm-jp-eval(v1.0.0) and JP Language Model Evaluation Harness(commit #9b42d41). The details are as follows:

• Multiple - choice question answering (JCommonsenseQA [Kurihara+, 2022])
• Open - ended question answering (JEMHopQA [Ishii+, 2023])
• Open - ended question answering (NIILC [Sekine, 2003])
• Machine reading comprehension (JSQuAD [Kurihara+, 2022])
• Automatic summarization (XL - Sum [Hasan+, 2021])
• Machine translation (WMT2020 ja - en [Barrault+, 2020])
• Machine translation (WMT2020 en - ja [Barrault+, 2020])
• Mathematical reasoning (MGSM [Shi+, 2023])

English evaluation benchmarks

We used the Language Model Evaluation Harness(v.0.3.0). The details are as follows:

• Multiple - choice question answering (OpenBookQA [Mihaylov+, 2018])
• Open - ended question answering (TriviaQA [Joshi+, 2017])
• Machine reading comprehension (SQuAD 2.0 [Rajpurkar+, 2018])
• Commonsense reasoning (XWINO [Tikhonov & Ryabinin, 2021])
• Natural language inference (HellaSwag [Zellers+, 2019])
• Mathematical reasoning (GSM8k [Cobbe+, 2021])

Training Datasets

Continual Pre - Training

The following datasets were used for continual pre - training.

• Japanese Wikipedia
• RefinedWeb
• Swallow Corpus
• The Pile

Instruction Tuning

The following datasets were used for the instruction tuning.

• Anthropic HH - RLHF
• Databricks Dolly 15 - k
• OpenAssistant Conversations Dataset

🔧 Technical Details

The Swallow model is based on the Llama 2 architecture. It uses a tokenizer with an expanded vocabulary based on Japanese data, which allows for more efficient text representation and faster inference. The model is continuously pre - trained with additional Japanese language data and tuned using supervised fine - tuning (SFT).

📄 License

Llama 2 is licensed under the LLAMA 2 Community License, Copyright © Meta Platforms, Inc. All Rights Reserved.

Acknowledgements

We thank Meta Research for releasing Llama 2 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.

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.

Authors

Here are the team members:

• From Okazaki Laboratory, the following members:
  • Naoaki Okazaki
  • Sakae Mizuki
  • Hiroki Iida
  • Mengsay Loem
  • Shota Hirai
  • Kakeru Hattori
  • Masanari Ohi
• From YOKOTA Laboratory, the following members:
  • Rio Yokota
  • Kazuki Fujii
  • Taishi Nakamura

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