metadata

language:
  - en
  - ja
license: apache-2.0
library_name: transformers
programming_language:
  - C
  - C++
  - C#
  - Go
  - Java
  - JavaScript
  - Lua
  - PHP
  - Python
  - Ruby
  - Rust
  - Scala
  - TypeScript
pipeline_tag: text-generation
inference: false
model-index:
  - name: llm-jp-13b-instruct-full-jaster-v1.0
    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: 27.22
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llm-jp/llm-jp-13b-instruct-full-jaster-v1.0
          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: 44.7
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llm-jp/llm-jp-13b-instruct-full-jaster-v1.0
          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: 23.12
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llm-jp/llm-jp-13b-instruct-full-jaster-v1.0
          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: 44.69
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llm-jp/llm-jp-13b-instruct-full-jaster-v1.0
          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: 50.04
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llm-jp/llm-jp-13b-instruct-full-jaster-v1.0
          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: 0
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=llm-jp/llm-jp-13b-instruct-full-jaster-v1.0
          name: Open LLM Leaderboard

llm-jp-13b-instruct-full-jaster-v1.0

This repository provides large language models developed by LLM-jp, a collaborative project launched in Japan.

Model Variant
Instruction models
llm-jp-13b-instruct-full-jaster-v1.0
llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0
llm-jp-13b-instruct-full-dolly-oasst-v1.0
llm-jp-13b-instruct-lora-jaster-v1.0
llm-jp-13b-instruct-lora-jaster-dolly-oasst-v1.0
llm-jp-13b-instruct-lora-dolly-oasst-v1.0


Pre-trained models
llm-jp-13b-v1.0
llm-jp-1.3b-v1.0
Checkpoints format: Hugging Face Transformers (Megatron-DeepSpeed format models are available here)

Required Libraries and Their Versions

torch>=2.0.0
transformers>=4.34.0
tokenizers>=0.14.0
accelerate==0.23.0

Usage

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("llm-jp/llm-jp-13b-instruct-full-jaster-v1.0")
model = AutoModelForCausalLM.from_pretrained("llm-jp/llm-jp-13b-instruct-full-jaster-v1.0", device_map="auto", torch_dtype=torch.float16)
text = "自然言語処理とは何か"
text = text + "### 回答："
tokenized_input = tokenizer.encode(text, add_special_tokens=False, return_tensors="pt").to(model.device)
with torch.no_grad():
    output = model.generate(
        tokenized_input,
        max_new_tokens=100,
        do_sample=True,
        top_p=0.95,
        temperature=0.7,
    )[0]
print(tokenizer.decode(output))

Model Details

Model type: Transformer-based Language Model
Total seen tokens: 300B

Model	Params	Layers	Hidden size	Heads	Context length
13b model	13b	40	5120	40	2048
1.3b model	1.3b	24	2048	16	2048

Training

Pre-training:
- Hardware: 96 A100 40GB GPUs (mdx cluster)
- Software: Megatron-DeepSpeed
Instruction tuning:
- Hardware: 8 A100 40GB GPUs (mdx cluster)
- Software: TRL, PEFT, and DeepSpeed

Tokenizer

The tokenizer of this model is based on huggingface/tokenizers Unigram byte-fallback model. The vocabulary entries were converted from llm-jp-tokenizer v2.1 (50k). Please refer to README.md of llm-ja-tokenizer for details on the vocabulary construction procedure.

Model: Hugging Face Fast Tokenizer using Unigram byte-fallback model which requires tokenizers>=0.14.0
Training algorithm: SentencePiece Unigram byte-fallback
Training data: A subset of the datasets for model pre-training
Vocabulary size: 50,570 (mixed vocabulary of Japanese, English, and source code)

Datasets

Pre-training

The models have been pre-trained using a blend of the following datasets.

Language	Dataset	Tokens
Japanese	Wikipedia	1.5B
	mC4	136B
English	Wikipedia	5B
	The Pile	135B
Codes	The Stack	10B

The pre-training was continuously conducted using a total of 10 folds of non-overlapping data, each consisting of approximately 27-28B tokens. We finalized the pre-training with additional (potentially) high-quality 27B tokens data obtained from the identical source datasets listed above used for the 10-fold data.

Instruction tuning

The models have been fine-tuned on the following datasets.

Language	Dataset	description
Japanese	jaster	An automatically transformed data from the existing Japanese NLP datasets
	databricks-dolly-15k	A translated one by DeepL in LLM-jp
	OpenAssistant Conversations Dataset	A translated one by DeepL in LLM-jp

Evaluation

You can view the evaluation results of several LLMs on this leaderboard. We used llm-jp-eval for the evaluation.

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.

Send Questions to

llm-jp(at)nii.ac.jp

License

Apache License, Version 2.0

Model Card Authors

The names are listed in alphabetical order.

Hirokazu Kiyomaru, Hiroshi Matsuda, Jun Suzuki, Namgi Han, Saku Sugawara, Shota Sasaki, Shuhei Kurita, Taishi Nakamura, Takumi Okamoto.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	31.63
AI2 Reasoning Challenge (25-Shot)	27.22
HellaSwag (10-Shot)	44.70
MMLU (5-Shot)	23.12
TruthfulQA (0-shot)	44.69
Winogrande (5-shot)	50.04
GSM8k (5-shot)	0.00