README.md

metadata

language:
  - ja
license: apache-2.0
tags:
  - japanese-stablelm
  - causal-lm
datasets:
  - wikipedia
  - mc4
  - cc100
  - oscar-corpus/OSCAR-2301
  - oscar-corpus/OSCAR-2201
  - cerebras/SlimPajama-627B
pipeline_tag: text-generation
extra_gated_fields:
  Name: text
  Email: text
  Country: text
  Organization or Affiliation: text
  I allow Stability AI to contact me about information related to its models and research: checkbox
model-index:
  - name: japanese-stablelm-base-gamma-7b
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 50.34
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/japanese-stablelm-base-gamma-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 77.47
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/japanese-stablelm-base-gamma-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 54.75
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/japanese-stablelm-base-gamma-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 41.2
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/japanese-stablelm-base-gamma-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 73.95
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/japanese-stablelm-base-gamma-7b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 17.82
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=stabilityai/japanese-stablelm-base-gamma-7b
          name: Open LLM Leaderboard

Japanese Stable LM Base Gamma 7B

Model Description

This is a 7B-parameter decoder-only language model with a focus on maximizing Japanese language modeling performance and Japanese downstream task performance. We conducted continued pretraining using Japanese data on the English language model, Mistral-7B-v0.1, to transfer the model's knowledge and capabilities to Japanese.

If you are looking for an instruction-following model, check Japanese Stable LM Instruct Gamma 7B.

If you are in search of a smaller model, please check Japanese StableLM-3B-4E1T Base.

Usage

Ensure you are using Transformers 4.34.0 or newer.

from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("stabilityai/japanese-stablelm-base-gamma-7b")
model = AutoModelForCausalLM.from_pretrained(
  "stabilityai/japanese-stablelm-base-gamma-7b",
  torch_dtype="auto",
)
model.cuda()
inputs = tokenizer("AI で科学研究を加速するには、", return_tensors="pt").to("cuda")
tokens = model.generate(
  **inputs,
  max_new_tokens=64,
  temperature=0.75,
  top_p=0.95,
  do_sample=True,
)
print(tokenizer.decode(tokens[0], skip_special_tokens=True))

Model Details

• Developed by: Stability AI
• Model type: Japanese Stable LM Base Gamma 7B model is an auto-regressive language model based on the transformer decoder architecture.
• Language(s): Japanese
• License: This model is licensed under Apache License, Version 2.0.
• Contact: For questions and comments about the model, please join Stable Community Japan. For future announcements / information about Stability AI models, research, and events, please follow https://twitter.com/StabilityAI_JP.

Model Architecture

For details, please see Mistral AI's paper and release blog post.

Training Dataset

Around 100B tokens from a mixture of the following corpora were used for the continued pretraining.

• Japanese/English Wikipedia
• Japanese mc4
• Japanese CC-100
• Japanese OSCAR
• SlimPajama without the Books3 subset

Use and Limitations

Intended Use

The model is intended to be used by all individuals as a foundational model for application-specific fine-tuning without strict limitations on commercial use.

Limitations and bias

The pre-training dataset may have contained offensive or inappropriate content even after applying data cleansing filters which can be reflected in the model-generated text. We recommend users exercise reasonable caution when using these models in production systems. Do not use the model for any applications that may cause harm or distress to individuals or groups.

Credits

The continued pre-training was carried out by Takuya Akiba. Other aspects, including data preparation and evaluation, were handled by the Language Team of Stability AI Japan, notably Meng Lee, Fujiki Nakamura, Makoto Shing, Paul McCann, and Naoki Orii.

Acknowledgements

This model is based on Mistral-7B-v0.1 released by the Mistral AI team. We are grateful to the Mistral AI team for providing such an excellent base model.

We are grateful for the contributions of the EleutherAI Polyglot-JA team in helping us to collect a large amount of pre-training data in Japanese. Polyglot-JA members includes Hyunwoong Ko (Project Lead), Fujiki Nakamura (originally started this project when he commited to the Polyglot team), Yunho Mo, Minji Jung, KeunSeok Im, and Su-Kyeong Jang.

We are also appreciative of AI Novelist/Sta (Bit192, Inc.) and the numerous contributors from Stable Community Japan for assisting us in gathering a large amount of high-quality Japanese textual data for model training.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	52.59
AI2 Reasoning Challenge (25-Shot)	50.34
HellaSwag (10-Shot)	77.47
MMLU (5-Shot)	54.75
TruthfulQA (0-shot)	41.20
Winogrande (5-shot)	73.95
GSM8k (5-shot)	17.82