kaisugi (Kaito Sugimoto)

upvoted a paper 5 days ago

LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs

Paper • 2407.03963 • Published 19 days ago • 13

upvoted a collection 17 days ago

DeBERTa V3

Collection

6 items • Updated 19 days ago • 1

upvoted a collection 22 days ago

neoAI LLM

Collection

1 item • Updated 28 days ago • 1

upvoted a collection 23 days ago

Llama-3-Swallow

Collection

4 items • Updated 23 days ago • 4

upvoted a collection 28 days ago

Llama-3-ELYZA-JP

Collection

Llama-3 models augmented for Japanese usage • 3 items • Updated 28 days ago • 4

upvoted an article 28 days ago

Article

Training MoE on AWS Trainium

By

•

May 23

• 4

upvoted 2 collections 29 days ago

KARAKURI LM Instruct

Collection

1 item • Updated Jun 19 • 1

KARAKURI LM Chat

Collection

2 items • Updated Jun 19 • 1

upvoted an article about 1 month ago

Article

An Analysis of Chinese LLM Censorship and Bias with Qwen 2 Instruct

By

•

Jun 11

• 42

upvoted a collection about 1 month ago

日本語LLM

Collection

162 items • Updated 15 days ago • 2

upvoted 2 collections about 2 months ago

Tanuki-8B

Collection

Llama-3-8B 類似アーキテクチャの日本語フルスクラッチLLM（NEDO承認後に公開予定） • 4 items • Updated Jun 12 • 3

shisa-v1

Collection

JA/EN Bilingual LLMs • 7 items • Updated May 27 • 1

upvoted an article about 2 months ago

Article

The Open Medical-LLM Leaderboard: Benchmarking Large Language Models in Healthcare

Apr 19

• 87

upvoted a paper 2 months ago

Tagengo: A Multilingual Chat Dataset

Paper • 2405.12612 • Published May 21 • 3

upvoted 2 articles 2 months ago

Article

Not Legal Advice on AI Training Data in Japan

By

•

May 25

• 1

Article

Evaling llm-jp-eval (evals are hard)

By

•

May 18

• 4

upvoted a paper 2 months ago

LEIA: Facilitating Cross-Lingual Knowledge Transfer in Language Models with Entity-based Data Augmentation

Paper • 2402.11485 • Published Feb 18 • 1

upvoted 3 papers 3 months ago

Construction of Domain-specified Japanese Large Language Model for Finance through Continual Pre-training

Paper • 2404.10555 • Published Apr 16 • 2

Pretraining and Updating Language- and Domain-specific Large Language Model: A Case Study in Japanese Business Domain

Paper • 2404.08262 • Published Apr 12 • 1

Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities

Paper • 2404.17790 • Published Apr 27 • 3

upvoted a paper 4 months ago

Release of Pre-Trained Models for the Japanese Language

Paper • 2404.01657 • Published Apr 2 • 1

upvoted 2 collections 4 months ago

Swallow-instruct

Collection

Swallow instruction tuning models • 8 items • Updated 26 days ago • 4

Swallow

Collection

Continual Pre-Training from Llama 2 • 7 items • Updated 26 days ago • 2

upvoted 2 collections 5 months ago

JaColBERT

Collection

4 items • Updated Mar 5 • 1

Kotomamba

Collection

State Space Model Mamba for Japanese and English • 2 items • Updated Feb 19 • 1

upvoted 2 collections 6 months ago

japanese-embedding-models

Collection

3 items • Updated Feb 3 • 1

KARAKURI LM

Collection

1 item • Updated Jun 19 • 3

upvoted 2 papers 6 months ago

JMedLoRA:Medical Domain Adaptation on Japanese Large Language Models using Instruction-tuning

Paper • 2310.10083 • Published Oct 16, 2023 • 2

JaColBERT and Hard Negatives, Towards Better Japanese-First Embeddings for Retrieval: Early Technical Report

Paper • 2312.16144 • Published Dec 26, 2023 • 3

upvoted 3 collections 6 months ago

upvoted 4 collections 7 months ago

ELYZA-japanese-CodeLlama-7b

Collection

CodeLlama models augmented for Japanese usage • 3 items • Updated 28 days ago • 2

ELYZA-japanese-Llama-2-13b

Collection

13b Llama-2 models augmented for Japanese usage • 5 items • Updated 28 days ago • 5

ELYZA-japanese-Llama-2-7b

Collection

7b Llama-2 models augmented for Japanese usage • 6 items • Updated 29 days ago • 4

nekomata

Collection

The nekomata model series are based on the Qwen series and have been continually pre-trained on Japanese-specific corpora. • 8 items • Updated 2 days ago • 5

upvoted a collection 8 months ago

Japanese Multimodal Models

Collection

Suite of multimodal models focusing on Japan/Japanese-related usage • 4 items • Updated Apr 8 • 6

upvoted 5 collections 9 months ago

Japanese Stable LM

Collection

Suite of LLMs focusing on Japanese usage • 15 items • Updated May 7 • 14

youri

Collection

The youri model series are based on the llama2 series and have been continually pre-trained on Japanese-specific corpora. • 6 items • Updated 2 days ago • 1

bilingual-gpt-neox-4b

Collection

The bilingual-gpt-neox-4b series are pre-trained from scratch on a mixture of Japanese and English corpora. • 5 items • Updated 2 days ago • 1

japanese-gpt-neox-3.6b

Collection

The japanese-gpt-neox-3.6b series are pre-trained from scratch on Japanese corpora. • 5 items • Updated 2 days ago • 2

language model

Collection

14 items • Updated 2 days ago • 3

Kaito Sugimoto

AI & ML interests

Organizations

kaisugi's activity

Training MoE on AWS Trainium

An Analysis of Chinese LLM Censorship and Bias with Qwen 2 Instruct

The Open Medical-LLM Leaderboard: Benchmarking Large Language Models in Healthcare

Not Legal Advice on AI Training Data in Japan

Evaling llm-jp-eval (evals are hard)