japanese-gpt-neox-3.6b

Overview

This repository provides a Japanese GPT-NeoX model of 3.6 billion parameters.

• Library

  The model was trained using code based on EleutherAI/gpt-neox.

• Model architecture

  A 36-layer, 2816-hidden-size transformer-based language model.

• Pre-training

  The model was trained on around 312.5B tokens from Japanese CC-100, Japanese C4, and Japanese Wikipedia to optimize a traditional language modelling objective.

  A final validation perplexity of 8.68 has been reached.

• Model Series

  Variant	Link
  3.6B PPO	https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-ppo
  3.6B SFT-v2	https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-sft-v2
  3.6B SFT	https://huggingface.co/rinna/japanese-gpt-neox-3.6b-instruction-sft
  3.6B pretrained	https://huggingface.co/rinna/japanese-gpt-neox-3.6b

• Authors

  Tianyu Zhao and Kei Sawada

How to use the model

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rinna/japanese-gpt-neox-3.6b", use_fast=False)
model = AutoModelForCausalLM.from_pretrained("rinna/japanese-gpt-neox-3.6b")

if torch.cuda.is_available():
    model = model.to("cuda")

text = "西田幾多郎は、"
token_ids = tokenizer.encode(text, add_special_tokens=False, return_tensors="pt")

with torch.no_grad():
    output_ids = model.generate(
        token_ids.to(model.device),
        max_new_tokens=100,
        min_new_tokens=100,
        do_sample=True,
        temperature=0.8,
        pad_token_id=tokenizer.pad_token_id,
        bos_token_id=tokenizer.bos_token_id,
        eos_token_id=tokenizer.eos_token_id
    )

output = tokenizer.decode(output_ids.tolist()[0])
print(output)
"""西田幾多郎は、この「絶対矛盾的自己同一」を「世界の自己同一」と置きかえ、さらに西田哲学を出発点として「絶対無」を「世界の成立」に変え、世界と自己を一つの統一物とみなす哲学として展開する。この世界と自己は絶対矛盾的自己同一として同一の性質を有し、同じ働きをする。西田哲学においては、この世界と自己は矛盾しあうのではなく、同一の性質をもっている。この世界と自己は同一である。絶対"""

Tokenization

The model uses a sentencepiece-based tokenizer.

• The tokenizer has a vocabulary size of 32,000.
• It uses sentencepiece's byte fallback feature to decompose unknown text pieces into UTF-8 byte pieces and to avoid producing <UNK> tokens.
• sentencepiece's --add_dummy_prefix option was turned off so that a leading whitespace will not be prepended automatically.

  print(tokenizer.tokenize("吾輩は猫である"))
  # ['吾', '輩', 'は', '猫', 'である']
  # instead of ['▁', '吾', '輩', 'は', '猫', 'である'] as in rinna/japanese-gpt-1b
  

• sentencepiece's --remove_extra_whitespaces option was turned off so that leading, trailing, and duplicate whitespaces are reserved.

  print(tokenizer.tokenize("  吾輩は  猫である   "))
  # ['▁', '▁', '吾', '輩', 'は', '▁', '▁', '猫', 'である', '▁', '▁', '▁']
  # instead of ['▁', '吾', '輩', 'は', '▁猫', 'である'] as in rinna/japanese-gpt-1b
  

• Don't forget to set use_fast=False to make the above features function correctly.

  good_tokenizer = AutoTokenizer.from_pretrained("rinna/japanese-gpt-neox-3.6b", use_fast=False)
  bad_tokenizer = AutoTokenizer.from_pretrained("rinna/japanese-gpt-neox-3.6b")
  
  print(good_tokenizer.decode(good_tokenizer.encode("გამარჯობა  吾輩は  猫である   ")))
  # 'გამარჯობა  吾輩は  猫である   </s>'
  print(bad_tokenizer.decode(bad_tokenizer.encode("გამარჯობა  吾輩は  猫である   ")))
  # 'გამარ[UNK]ობა 吾輩は 猫である </s>'
  

Licenese

The MIT license