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

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

This model is based on llm-jp/llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0 .

This version does not have Tokenizer postprocessing (i.e. adding eos token) so there is no need to specify add_special_tokens=False on tokenize.

---

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

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-dolly-oasst-v1.0")
model = AutoModelForCausalLM.from_pretrained("llm-jp/llm-jp-13b-instruct-full-jaster-dolly-oasst-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, 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

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.

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.

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.