Hiroki Sakaji

The University of Tokyo

7-3-1 Hongo

Bunkyo-ku

Tokyo, 113-0033

Japan

  • The University of Tokyo

SCHOLARLY PAPERS

3

DOWNLOADS

117

TOTAL CITATIONS

5

Scholarly Papers (3)

Actions:
Email selected abstracts
1.

LLM-Japanese-Dataset v0: Construction of Japanese Chat Dataset for Large Language Models and its Methodology

Number of pages: 12 Posted: 07 Jun 2023
Masanori Hirano, Masahiro Suzuki and Hiroki Sakaji
Preferred Networks, Inc., University of Tokyo and The University of Tokyo
Downloads 56 (723,825)
Citation 3

Abstract:

Loading...

Large Language Model, Dataset, Japanese, Chat

2.

From Base to Conversational: Japanese Instruction Dataset and Tuning Large Language Models

Number of pages: 10 Posted: 26 Sep 2023
Masahiro Suzuki, Masanori Hirano and Hiroki Sakaji
University of Tokyo, Preferred Networks, Inc. and The University of Tokyo
Downloads 42 (816,093)

Abstract:

Loading...

Large Language Model (LLM), Instruction Dataset, Instruction Tuning, Japanese

3.

Policy Gradient Stock Gan for Realistic Discrete Order Data Generation in Financial Markets

Number of pages: 21 Posted: 03 May 2022
Masanori Hirano, Hiroki Sakaji and Kiyoshi Izumi
Preferred Networks, Inc., The University of Tokyo and University of Tokyo - School of Engineering
Downloads 19 (1,027,036)
Citation 2

Abstract:

Loading...

Generative adversarial networks (GAN), Financial markets, Policy gradient, Order generation