LLM-jp

Team

university

https://llm-jp.nii.ac.jp/en/

llm_jp

llm-jp

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

speed new activity 3 days ago

llm-jp/llm-jp-4-vl-9b:Add image-text-to-text pipeline tag

speed published a dataset 4 days ago

llm-jp/RefinedVision

speed updated a dataset 4 days ago

llm-jp/RefinedVision

View all activity

Papers

HakushoBench: A Japanese Chart and Table VQA Benchmark from Governmental White Papers

Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models

View all Papers

llm-jp 's collections 17

LLM-jp-4 Models

llm-jp/llm-jp-4-33b-thinking

Text Generation • 33B • Updated 21 days ago • 16.6k • 39
llm-jp/llm-jp-4-33b-thinking-gguf

Text Generation • 33B • Updated 16 days ago • 4.84k • 10
llm-jp/llm-jp-4-33b-base

Text Generation • 33B • Updated 21 days ago • 258 • 8
llm-jp/llm-jp-4-32b-a3b-thinking

Text Generation • 32B • Updated Apr 24 • 3.56k • 38

WAON

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 Oct 25, 2025 • 3
llm-jp/WAON-Bench

Viewer • Updated Apr 13 • 1.87k • 425 • 2
llm-jp/waon-siglip2-base-patch16-256

Zero-Shot Image Classification • 0.4B • Updated Nov 2, 2025 • 785 • 1
llm-jp/WAON

Updated Nov 6, 2025 • 93 • 8

Optimal Sparsity Code

Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks

llm-jp/optimal-sparsity-code-d512-E8-k2-320M-A170M

Text Generation • 0.3B • Updated Feb 19 • 246
llm-jp/optimal-sparsity-code-d512-E16-k2-520M-A170M

Text Generation • 0.5B • Updated Feb 19 • 163
llm-jp/optimal-sparsity-code-d512-E32-k2-920M-A170M

Text Generation • 0.9B • Updated Feb 19 • 124
llm-jp/optimal-sparsity-code-d512-E64-k2-1.7B-A170M

Text Generation • 2B • Updated Feb 19 • 84

LLM-jp-3.1 Fine-tuned Models

Fine-tuned models in the LLM-jp-3 model series

llm-jp/llm-jp-3.1-8x13b-instruct4

Text Generation • 73B • Updated May 30, 2025 • 136 • 4
llm-jp/llm-jp-3.1-8x13b-32K-instruct4

Text Generation • 73B • Updated Feb 25 • 74 • 2
llm-jp/llm-jp-3.1-13b-instruct4

Text Generation • 14B • Updated May 30, 2025 • 1.04k • 19
llm-jp/llm-jp-3.1-1.8b-instruct4

Text Generation • 2B • Updated May 30, 2025 • 1.14k • 21

Open Japanese LLM leaderboard

Runtime error

Agents

108

Open Japanese LLM Leaderboard

🌸

108

Explore and compare LLM models with interactive filters and visualizations
llm-jp/leaderboard-requests

Viewer • Updated Oct 23, 2025 • 3 • 15.9k • 2
llm-jp/leaderboard-contents

Viewer • Updated Oct 23, 2025 • 862 • 87 • 1
llm-jp/leaderboard-results

Updated Oct 23, 2025 • 6.79k • 1

Drop-Upcycling

llm-jp/FS-8x1.5B

9B • Updated Feb 27, 2025 • 52
llm-jp/BTX-8x1.5B

9B • Updated Feb 27, 2025 • 57
llm-jp/FS-8x3.7B

19B • Updated Feb 27, 2025 • 51
llm-jp/NU-8x1.5B

9B • Updated Feb 27, 2025 • 56

LLM-jp-3.1 Pre-trained Models

Pre-trained models in the LLM-jp-3.1 model series

llm-jp/llm-jp-3.1-8x13b

Text Generation • 73B • Updated May 30, 2025 • 55
llm-jp/llm-jp-3.1-8x13b-32K

Text Generation • 73B • Updated Feb 25 • 62 • 1
llm-jp/llm-jp-3.1-13b

Text Generation • 14B • Updated May 30, 2025 • 93 • 2
llm-jp/llm-jp-3.1-1.8b

Text Generation • 2B • Updated May 30, 2025 • 941 • 14

LLM-jp ver2.0 Models

Models in the LLM-jp ver2.0 model series

llm-jp/llm-jp-13b-v2.0

Text Generation • Updated Apr 30, 2024 • 79 • 15
llm-jp/llm-jp-13b-instruct-full-dolly-ichikara_004_001_single-oasst-oasst2-v2.0

Text Generation • 14B • Updated Apr 30, 2024 • 66
llm-jp/llm-jp-13b-instruct-full-ac_001-dolly-ichikara_004_001_single-oasst-oasst2-v2.0

Text Generation • 14B • Updated Apr 30, 2024 • 66 • 1
llm-jp/llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0

Text Generation • 14B • Updated Apr 30, 2024 • 65 • 3

LLM-jp ver1.0 Models

Models in the LLM-jp ver1.0 model series

llm-jp/llm-jp-13b-v1.0

Text Generation • Updated Oct 20, 2023 • 266 • 41
llm-jp/llm-jp-13b-instruct-full-jaster-v1.0

Text Generation • Updated Oct 20, 2023 • 148 • 15
llm-jp/llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0

Text Generation • Updated Oct 20, 2023 • 137 • 8
llm-jp/llm-jp-13b-instruct-full-dolly-oasst-v1.0

Text Generation • Updated Oct 20, 2023 • 125 • 4

Jagle

Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision–Language Models

llm-jp/Jagle

Updated May 12 • 287 • 17
llm-jp/Jagle-VL-2.2B-Jagle-FineVision

Feature Extraction • 2B • Updated May 25 • 68 • 4
llm-jp/Jagle-VL-2.2B-FineVision

Feature Extraction • 2B • Updated May 10 • 54 • 1
llm-jp/Jagle-VL-2.2B-Jagle

Feature Extraction • 2B • Updated Apr 13 • 248 • 4

Llama-Mimi

Llama-Mimi: Speech Language Models with Interleaved Semantic and Acoustic Tokens

llm-jp/Llama-Mimi-1.3B

Audio-to-Audio • 1B • Updated Oct 2, 2025 • 231 • 11
llm-jp/Llama-Mimi-8B

Audio-to-Audio • 8B • Updated Sep 19, 2025 • 103 • 12
Llama-Mimi: Speech Language Models with Interleaved Semantic and Acoustic Tokens

Paper • 2509.14882 • Published Sep 18, 2025 • 2

Optimal Sparsity Math

Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks

llm-jp/optimal-sparsity-math-d512-E8-k2-320M-A170M

Text Generation • 0.3B • Updated Feb 19 • 61
llm-jp/optimal-sparsity-math-d512-E16-k2-520M-A170M

Text Generation • 0.5B • Updated Feb 19 • 53
llm-jp/optimal-sparsity-math-d512-E32-k2-920M-A170M

Text Generation • 0.9B • Updated Feb 19 • 49
llm-jp/optimal-sparsity-math-d512-E64-k2-1.7B-A170M

Text Generation • 2B • Updated Feb 19 • 61

LLM-jp-3 Fine-tuned Models

Fine-tuned models in the LLM-jp-3 model series

llm-jp/llm-jp-3-8x13b-instruct3

Text Generation • 73B • Updated Apr 1, 2025 • 147 • 8
llm-jp/llm-jp-3-172b-instruct3

Text Generation • 172B • Updated Jan 20, 2025 • 155 • 11
llm-jp/llm-jp-3-13b-instruct3

Text Generation • 14B • Updated Feb 4, 2025 • 352 • 8
llm-jp/llm-jp-3-8x1.8b-instruct3

Text Generation • 9B • Updated Apr 1, 2025 • 66 • 4

Multi Modal Models

llm-jp/HakushoBench

Viewer • Updated Jun 3 • 2.05k • 478 • 4
llm-jp/relaion2B-en-research-safe-japanese-translation

Viewer • Updated Apr 30, 2025 • 2.1B • 908 • 4
llm-jp/JAMMEval

Viewer • Updated Apr 8 • 1.59k • 729 • 5
llm-jp/llm-jp-3-vila-14b

Image-Text-to-Text • Updated Nov 18, 2024 • 78 • 11

Sparse Autoencoders

llm-jp/llm-jp-3-1.8b-sae-l12-k32-16x-c988240

0.1B • Updated Mar 12, 2025 • 47
llm-jp/llm-jp-3-1.8b-sae-l12-k32-16x-c100000

Updated Mar 18, 2025
llm-jp/llm-jp-3-1.8b-sae-l12-k32-16x-c10000

Updated Mar 18, 2025
llm-jp/llm-jp-3-1.8b-sae-l12-k32-16x-c1000

Updated Mar 18, 2025

LLM-jp-3 Pre-trained Models

Pre-trained models in the LLM-jp-3 model series

llm-jp/llm-jp-3-8x13b

Text Generation • 73B • Updated Mar 27, 2025 • 61
llm-jp/llm-jp-3-172b

Text Generation • 172B • Updated Dec 23, 2024 • 5
llm-jp/llm-jp-3-8x1.8b

Text Generation • 9B • Updated Mar 27, 2025 • 123
llm-jp/llm-jp-3-13b

Text Generation • 14B • Updated Sep 26, 2024 • 404 • 13

LLM-jp ver1.1 Models

Models in the LLM-jp ver1.1 model series

llm-jp/llm-jp-13b-dpo-lora-hh_rlhf_ja-v1.1

Text Generation • Updated Mar 12, 2024 • 1
llm-jp/llm-jp-13b-instruct-full-dolly_en-dolly_ja-ichikara_003_001-oasst_en-oasst_ja-v1.1

Text Generation • 13B • Updated Feb 7, 2024 • 72 • 2
llm-jp/llm-jp-13b-instruct-lora-dolly_en-dolly_ja-ichikara_003_001-oasst_en-oasst_ja-v1.1

Text Generation • Updated Mar 12, 2024 • 1

LLM-jp-4 Models

llm-jp/llm-jp-4-33b-thinking

Text Generation • 33B • Updated 21 days ago • 16.6k • 39
llm-jp/llm-jp-4-33b-thinking-gguf

Text Generation • 33B • Updated 16 days ago • 4.84k • 10
llm-jp/llm-jp-4-33b-base

Text Generation • 33B • Updated 21 days ago • 258 • 8
llm-jp/llm-jp-4-32b-a3b-thinking

Text Generation • 32B • Updated Apr 24 • 3.56k • 38

Jagle

Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision–Language Models

llm-jp/Jagle

Updated May 12 • 287 • 17
llm-jp/Jagle-VL-2.2B-Jagle-FineVision

Feature Extraction • 2B • Updated May 25 • 68 • 4
llm-jp/Jagle-VL-2.2B-FineVision

Feature Extraction • 2B • Updated May 10 • 54 • 1
llm-jp/Jagle-VL-2.2B-Jagle

Feature Extraction • 2B • Updated Apr 13 • 248 • 4

WAON

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 Oct 25, 2025 • 3
llm-jp/WAON-Bench

Viewer • Updated Apr 13 • 1.87k • 425 • 2
llm-jp/waon-siglip2-base-patch16-256

Zero-Shot Image Classification • 0.4B • Updated Nov 2, 2025 • 785 • 1
llm-jp/WAON

Updated Nov 6, 2025 • 93 • 8

Llama-Mimi

Llama-Mimi: Speech Language Models with Interleaved Semantic and Acoustic Tokens

llm-jp/Llama-Mimi-1.3B

Audio-to-Audio • 1B • Updated Oct 2, 2025 • 231 • 11
llm-jp/Llama-Mimi-8B

Audio-to-Audio • 8B • Updated Sep 19, 2025 • 103 • 12
Llama-Mimi: Speech Language Models with Interleaved Semantic and Acoustic Tokens

Paper • 2509.14882 • Published Sep 18, 2025 • 2

Optimal Sparsity Code

Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks

llm-jp/optimal-sparsity-code-d512-E8-k2-320M-A170M

Text Generation • 0.3B • Updated Feb 19 • 246
llm-jp/optimal-sparsity-code-d512-E16-k2-520M-A170M

Text Generation • 0.5B • Updated Feb 19 • 163
llm-jp/optimal-sparsity-code-d512-E32-k2-920M-A170M

Text Generation • 0.9B • Updated Feb 19 • 124
llm-jp/optimal-sparsity-code-d512-E64-k2-1.7B-A170M

Text Generation • 2B • Updated Feb 19 • 84

Optimal Sparsity Math

Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks

llm-jp/optimal-sparsity-math-d512-E8-k2-320M-A170M

Text Generation • 0.3B • Updated Feb 19 • 61
llm-jp/optimal-sparsity-math-d512-E16-k2-520M-A170M

Text Generation • 0.5B • Updated Feb 19 • 53
llm-jp/optimal-sparsity-math-d512-E32-k2-920M-A170M

Text Generation • 0.9B • Updated Feb 19 • 49
llm-jp/optimal-sparsity-math-d512-E64-k2-1.7B-A170M

Text Generation • 2B • Updated Feb 19 • 61

LLM-jp-3.1 Fine-tuned Models

Fine-tuned models in the LLM-jp-3 model series

llm-jp/llm-jp-3.1-8x13b-instruct4

Text Generation • 73B • Updated May 30, 2025 • 136 • 4
llm-jp/llm-jp-3.1-8x13b-32K-instruct4

Text Generation • 73B • Updated Feb 25 • 74 • 2
llm-jp/llm-jp-3.1-13b-instruct4

Text Generation • 14B • Updated May 30, 2025 • 1.04k • 19
llm-jp/llm-jp-3.1-1.8b-instruct4

Text Generation • 2B • Updated May 30, 2025 • 1.14k • 21

LLM-jp-3 Fine-tuned Models

Fine-tuned models in the LLM-jp-3 model series

llm-jp/llm-jp-3-8x13b-instruct3

Text Generation • 73B • Updated Apr 1, 2025 • 147 • 8
llm-jp/llm-jp-3-172b-instruct3

Text Generation • 172B • Updated Jan 20, 2025 • 155 • 11
llm-jp/llm-jp-3-13b-instruct3

Text Generation • 14B • Updated Feb 4, 2025 • 352 • 8
llm-jp/llm-jp-3-8x1.8b-instruct3

Text Generation • 9B • Updated Apr 1, 2025 • 66 • 4

Open Japanese LLM leaderboard

Runtime error

Agents

108

Open Japanese LLM Leaderboard

🌸

108

Explore and compare LLM models with interactive filters and visualizations
llm-jp/leaderboard-requests

Viewer • Updated Oct 23, 2025 • 3 • 15.9k • 2
llm-jp/leaderboard-contents

Viewer • Updated Oct 23, 2025 • 862 • 87 • 1
llm-jp/leaderboard-results

Updated Oct 23, 2025 • 6.79k • 1

Multi Modal Models

llm-jp/HakushoBench

Viewer • Updated Jun 3 • 2.05k • 478 • 4
llm-jp/relaion2B-en-research-safe-japanese-translation

Viewer • Updated Apr 30, 2025 • 2.1B • 908 • 4
llm-jp/JAMMEval

Viewer • Updated Apr 8 • 1.59k • 729 • 5
llm-jp/llm-jp-3-vila-14b

Image-Text-to-Text • Updated Nov 18, 2024 • 78 • 11

Drop-Upcycling

llm-jp/FS-8x1.5B

9B • Updated Feb 27, 2025 • 52
llm-jp/BTX-8x1.5B

9B • Updated Feb 27, 2025 • 57
llm-jp/FS-8x3.7B

19B • Updated Feb 27, 2025 • 51
llm-jp/NU-8x1.5B

9B • Updated Feb 27, 2025 • 56

Sparse Autoencoders

llm-jp/llm-jp-3-1.8b-sae-l12-k32-16x-c988240

0.1B • Updated Mar 12, 2025 • 47
llm-jp/llm-jp-3-1.8b-sae-l12-k32-16x-c100000

Updated Mar 18, 2025
llm-jp/llm-jp-3-1.8b-sae-l12-k32-16x-c10000

Updated Mar 18, 2025
llm-jp/llm-jp-3-1.8b-sae-l12-k32-16x-c1000

Updated Mar 18, 2025

LLM-jp-3.1 Pre-trained Models

Pre-trained models in the LLM-jp-3.1 model series

llm-jp/llm-jp-3.1-8x13b

Text Generation • 73B • Updated May 30, 2025 • 55
llm-jp/llm-jp-3.1-8x13b-32K

Text Generation • 73B • Updated Feb 25 • 62 • 1
llm-jp/llm-jp-3.1-13b

Text Generation • 14B • Updated May 30, 2025 • 93 • 2
llm-jp/llm-jp-3.1-1.8b

Text Generation • 2B • Updated May 30, 2025 • 941 • 14

LLM-jp-3 Pre-trained Models

Pre-trained models in the LLM-jp-3 model series

llm-jp/llm-jp-3-8x13b

Text Generation • 73B • Updated Mar 27, 2025 • 61
llm-jp/llm-jp-3-172b

Text Generation • 172B • Updated Dec 23, 2024 • 5
llm-jp/llm-jp-3-8x1.8b

Text Generation • 9B • Updated Mar 27, 2025 • 123
llm-jp/llm-jp-3-13b

Text Generation • 14B • Updated Sep 26, 2024 • 404 • 13

LLM-jp ver2.0 Models

Models in the LLM-jp ver2.0 model series

llm-jp/llm-jp-13b-v2.0

Text Generation • Updated Apr 30, 2024 • 79 • 15
llm-jp/llm-jp-13b-instruct-full-dolly-ichikara_004_001_single-oasst-oasst2-v2.0

Text Generation • 14B • Updated Apr 30, 2024 • 66
llm-jp/llm-jp-13b-instruct-full-ac_001-dolly-ichikara_004_001_single-oasst-oasst2-v2.0

Text Generation • 14B • Updated Apr 30, 2024 • 66 • 1
llm-jp/llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0

Text Generation • 14B • Updated Apr 30, 2024 • 65 • 3

LLM-jp ver1.1 Models

Models in the LLM-jp ver1.1 model series

llm-jp/llm-jp-13b-dpo-lora-hh_rlhf_ja-v1.1

Text Generation • Updated Mar 12, 2024 • 1
llm-jp/llm-jp-13b-instruct-full-dolly_en-dolly_ja-ichikara_003_001-oasst_en-oasst_ja-v1.1

Text Generation • 13B • Updated Feb 7, 2024 • 72 • 2
llm-jp/llm-jp-13b-instruct-lora-dolly_en-dolly_ja-ichikara_003_001-oasst_en-oasst_ja-v1.1

Text Generation • Updated Mar 12, 2024 • 1

LLM-jp ver1.0 Models

Models in the LLM-jp ver1.0 model series

llm-jp/llm-jp-13b-v1.0

Text Generation • Updated Oct 20, 2023 • 266 • 41
llm-jp/llm-jp-13b-instruct-full-jaster-v1.0

Text Generation • Updated Oct 20, 2023 • 148 • 15
llm-jp/llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0

Text Generation • Updated Oct 20, 2023 • 137 • 8
llm-jp/llm-jp-13b-instruct-full-dolly-oasst-v1.0

Text Generation • Updated Oct 20, 2023 • 125 • 4

AI & ML interests

Recent Activity

Papers

Team members 42

llm-jp 's collections 17

Open Japanese LLM Leaderboard

Open Japanese LLM Leaderboard