Hugging Face's logo

RichardErkhov
/
tokyotech-llm_-_Swallow-MS-7b-instruct-v0.1-gguf

GGUF
Inference Endpoints
conversational
Model card Files Community
Edit model card
YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Swallow-MS-7b-instruct-v0.1 - GGUF

Name Quant method Size
Swallow-MS-7b-instruct-v0.1.Q2_K.gguf Q2_K 2.58GB
Swallow-MS-7b-instruct-v0.1.IQ3_XS.gguf IQ3_XS 2.86GB
Swallow-MS-7b-instruct-v0.1.IQ3_S.gguf IQ3_S 3.02GB
Swallow-MS-7b-instruct-v0.1.Q3_K_S.gguf Q3_K_S 3.0GB
Swallow-MS-7b-instruct-v0.1.IQ3_M.gguf IQ3_M 3.11GB
Swallow-MS-7b-instruct-v0.1.Q3_K.gguf Q3_K 3.33GB
Swallow-MS-7b-instruct-v0.1.Q3_K_M.gguf Q3_K_M 3.33GB
Swallow-MS-7b-instruct-v0.1.Q3_K_L.gguf Q3_K_L 3.61GB
Swallow-MS-7b-instruct-v0.1.IQ4_XS.gguf IQ4_XS 3.73GB
Swallow-MS-7b-instruct-v0.1.Q4_0.gguf Q4_0 3.88GB
Swallow-MS-7b-instruct-v0.1.IQ4_NL.gguf IQ4_NL 3.93GB
Swallow-MS-7b-instruct-v0.1.Q4_K_S.gguf Q4_K_S 3.91GB
Swallow-MS-7b-instruct-v0.1.Q4_K.gguf Q4_K 4.13GB
Swallow-MS-7b-instruct-v0.1.Q4_K_M.gguf Q4_K_M 4.13GB
Swallow-MS-7b-instruct-v0.1.Q4_1.gguf Q4_1 4.3GB
Swallow-MS-7b-instruct-v0.1.Q5_0.gguf Q5_0 4.72GB
Swallow-MS-7b-instruct-v0.1.Q5_K_S.gguf Q5_K_S 4.72GB
Swallow-MS-7b-instruct-v0.1.Q5_K.gguf Q5_K 4.84GB
Swallow-MS-7b-instruct-v0.1.Q5_K_M.gguf Q5_K_M 4.84GB
Swallow-MS-7b-instruct-v0.1.Q5_1.gguf Q5_1 5.13GB
Swallow-MS-7b-instruct-v0.1.Q6_K.gguf Q6_K 5.6GB
Swallow-MS-7b-instruct-v0.1.Q8_0.gguf Q8_0 7.26GB

Original model description:

language: - en - ja library_name: transformers pipeline_tag: text-generation model_type: mistral license: apache-2.0

Swallow-MS-7b-v0.1

Our Swallow-MS-7b-v0.1 model has undergone continual pre-training from the Mistral-7B-v0.1, primarily with the addition of Japanese language data.

Model Release Updates

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

This repository provides large language models developed by TokyoTech-LLM.

Model Details

  • Model type: Please refer to Mistral technical report for details on the model architecture.
  • Language(s): Japanese English
  • Tokenizer: This model employs a tokenizer that features a broadened vocabulary based on Japanese data. This allows for a more efficient representation of text using fewer tokens, leading to a notably faster inference process.
  • Contact: swallow[at]nlp.c.titech.ac.jp

Instruct Model Performance

MT-Bench JA

Turn-Wise Performance

We report overall (i.e., average over scores of the first and second turns), first, and second turn scores.

Overall
Model Average Writing Roleplay Reasoning Math Coding Extraction STEM Humanities
Swallow-MS-7b-instruct-v0.1 0.3411 0.3770 0.4290 0.3454 0.1040 0.2400 0.3677 0.3907 0.4750
First Turn
Model Average Writing Roleplay Reasoning Math Coding Extraction STEM Humanities
Swallow-MS-7b-instruct-v0.1 0.3699 0.4880 0.4260 0.3900 0.1080 0.2364 0.3780 0.4500 0.4800
Second Turn
Model Average Writing Roleplay Reasoning Math Coding Extraction STEM Humanities
Swallow-MS-7b-instruct-v0.1 0.3130 0.2624 0.4320 0.2996 0.1000 0.2430 0.3564 0.3291 0.4700

Comparison to the past model

We only provide the overall score in this section.

Model Average Writing Roleplay Reasoning Math Coding Extraction STEM Humanities
Swallow-MS-7b-instruct-v0.1 0.3411 0.3770 0.4290 0.3454 0.1040 0.2400 0.3677 0.3907 0.4750
ELYZA-japanese-Llama-2-7b-fast-instruct 0.2827 0.3289 0.3907 0.2424 0.1480 0.1584 0.3511 0.3053 0.3365
calm2-7b-chat 0.3204 0.4657 0.4898 0.1837 0.1005 0.1414 0.3927 0.3601 0.4293
calm2-7b-chat-dpo-experimental 0.3493 0.5312 0.5237 0.1857 0.1000 0.1813 0.3355 0.4320 0.5051
RakutenAI-7B-instruct 0.2994 0.3623 0.3711 0.3333 0.1763 0.1581 0.4215 0.2824 0.2901
RakutenAI-7B-chat 0.3667 0.4229 0.4644 0.3990 0.2161 0.2390 0.3416 0.3904 0.4601

Evaluation Benchmarks

MT-Bench JA

We used Japanese MT-Bench to assess the instruction-following capabilities of models. We utilized the following settings:

Usage

First install additional dependencies in requirements.txt:

pip install -r requirements.txt

Instruction format Ver0.1

This format must be adhered to strictly, as deviations may result in less optimal outputs from the model.

The template used to construct a prompt for the Instruct model is specified as follows:

<s>[INST] <<SYS>>\n{SYSTEM_PROMPT}\n<</SYS>>\n\n{USER_MESSAGE_1} [/INST] {BOT_MESSAGE_1}</s>[INST] {USER_MESSAGE_2} [/INST]

Please be aware that <s> and </s> are special tokens used for the beginning of string (BOS) and end of string (EOS), respectively, while [INST] and [/INST] are considered regular strings.

For the "{SYSTEM_PROMPT}" part, We recommend using "あなたは誠実で優秀な日本人のアシスタントです。"

For the "{USER_MESSAGE_1}" part, We recommend using {instruction}\n{input}

In other words, We recommend the following:

<s>[INST] <<SYS>>\nあなたは誠実で優秀な日本人のアシスタントです。\n<</SYS>>\n\n{instruction1}\n{input1} [/INST] {BOT_MESSAGE_1}</s>[INST] {instruction2}\n{input2} [/INST]

Use the instruct model Ver0.1 

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "tokyotech-llm/Swallow-MS-7b-instruct-v0.1"
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

device = "cuda"

messages = [
    {"role": "system", "content": "あなたは誠実で優秀な日本人のアシスタントです。"},
    {"role": "user", "content": "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"}
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=128, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])

Training Datasets

Instruction Tuning Ver0.1

The following datasets were used for the instruction tuning.

Please note that some of the data had issues with quality or format, so not all of it was used.

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 Mistral 7B 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.

License

apache-2.0

Authors

Here are the team members:

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},
}
Downloads last month
301
GGUF
Model size
7.33B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

View +2 files
Inference API
Unable to determine this model's library. Check the docs .