-
llm-jp/llm-jp-4-8b-base
Text Generation • 9B • Updated • 1.23k • 5 -
llm-jp/llm-jp-4-8b-thinking
Text Generation • 9B • Updated • 15.3k • 26 -
llm-jp/llm-jp-4-32b-a3b-base
Text Generation • 32B • Updated • 157 • 5 -
llm-jp/llm-jp-4-32b-a3b-thinking
Text Generation • 32B • Updated • 5.85k • 21
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models
JAMMEval: A Refined Collection of Japanese Benchmarks for Reliable VLM Evaluation
Organization Card
LLM-jp consists of over 1,000 participants, including researchers and engineers in natural language processing and computer systems from universities and corporations organized under the auspices of the National Institute of Informatics (NII) in Tokyo, Japan. The main goals are to collaboratively work on building open-source LLMs that are proficient in Japanese, to share information on LLM research and development, to promote cross-organizational collaborations among researchers, to release models, tools, and technical materials to the public. For more details, please refer to our website and paper.
Links
- Website: https://llm-jp.nii.ac.jp/en/
- Model: See the Collections section below.
- Corpus: See https://gitlab.llm-jp.nii.ac.jp/datasets.
- LLM-jp Chatbot Arena: Visit https://chatbot-arena.apps.llmc.nii.ac.jp/ to try our latest models.
WAON: Large-Scale and High-Quality Japanese Image-Text Pair Dataset for Vision-Language Models
-
WAON: Large-Scale and High-Quality Japanese Image-Text Pair Dataset for Vision-Language Models
Paper • 2510.22276 • Published • 3 -
llm-jp/WAON-Bench
Viewer • Updated • 1.87k • 217 • 1 -
llm-jp/waon-siglip2-base-patch16-256
Zero-Shot Image Classification • 0.4B • Updated • 71 • 1 -
llm-jp/WAON
Updated • 83 • 7
-
llm-jp/llm-jp-4-8b-base
Text Generation • 9B • Updated • 1.23k • 5 -
llm-jp/llm-jp-4-8b-thinking
Text Generation • 9B • Updated • 15.3k • 26 -
llm-jp/llm-jp-4-32b-a3b-base
Text Generation • 32B • Updated • 157 • 5 -
llm-jp/llm-jp-4-32b-a3b-thinking
Text Generation • 32B • Updated • 5.85k • 21
WAON: Large-Scale and High-Quality Japanese Image-Text Pair Dataset for Vision-Language Models
-
WAON: Large-Scale and High-Quality Japanese Image-Text Pair Dataset for Vision-Language Models
Paper • 2510.22276 • Published • 3 -
llm-jp/WAON-Bench
Viewer • Updated • 1.87k • 217 • 1 -
llm-jp/waon-siglip2-base-patch16-256
Zero-Shot Image Classification • 0.4B • Updated • 71 • 1 -
llm-jp/WAON
Updated • 83 • 7
models 255
llm-jp/llm-jp-4-32b-a3b-thinking
Text Generation • 32B • Updated • 5.85k • 21
llm-jp/llm-jp-4-8b-thinking
Text Generation • 9B • Updated • 15.3k • 26
llm-jp/llm-jp-4-8b-base
Text Generation • 9B • Updated • 1.23k • 5
llm-jp/llm-jp-4-32b-a3b-base
Text Generation • 32B • Updated • 157 • 5
llm-jp/llm-jp-moshi-v1
Updated • 590 • 36
llm-jp/llm-jp-3.1-8x13b-32K
Text Generation • 73B • Updated • 16 • 1
llm-jp/llm-jp-3.1-8x13b-32K-instruct4
Text Generation • 73B • Updated • 44 • 2
llm-jp/optimal-sparsity-code-d2048-E128-k16-52.2B-A7.1B
Text Generation • 52B • Updated • 4
llm-jp/optimal-sparsity-code-d2048-E64-k16-26.4B-A7.1B
Text Generation • 26B • Updated • 1
llm-jp/optimal-sparsity-code-d2048-E32-k16-13.6B-A7.1B
Text Generation • 14B • Updated • 1
datasets 45
llm-jp/leaderboard-requests-v2
Viewer • Updated • 12 • 535
llm-jp/JAMMEval
Viewer • Updated • 1.59k • 434 • 2
llm-jp/llm-jp-4-32b-a3b-thinking-dpo-data
Viewer • Updated • 155k • 103 • 1
llm-jp/llm-jp-4-8b-thinking-dpo-data
Viewer • Updated • 183k • 106 • 1
llm-jp/llm-jp-4-thinking-sft-data
Viewer • Updated • 3.2M • 168 • 1
llm-jp/scaling-data-constrained-llms
Viewer • Updated • 556M • 214 • 2
llm-jp/leaderboard-contents-v2
Viewer • Updated • 4 • 540 • 1
llm-jp/llm-jp-longbench-NIILC
Viewer • Updated • 10 • 18 • 1
llm-jp/llm-jp-longbench-JEMHop
Viewer • Updated • 90 • 18
llm-jp/AnswerCarefully
Viewer • Updated • 4.62k • 309 • 51