
Summary of Japanese LLM (Open Source)
Description in other languages
Statistics
Statistics as of Nov 17, 2026
GitHub stars
1,400
±0 (Oct 13〜)
Last commit
Nov 2026
Created on GitHub
Jul 9, 2023
Listed
Jul 24, 2023
Stars over time
Show as a table
| Month | Stars |
|---|---|
| Dec 2025 | 1,300 |
| Jan 2026 | 1,300 |
| Feb 2026 | 1,300 |
| Mar 2026 | 1,400 |
| Apr 2026 | 1,400 |
| May 2026 | 1,400 |
| Jun 2026 | 1,400 |
| Jul 2026 | 1,400 |
| Aug 2026 | 1,400 |
| Sep 2026 | 1,400 |
| Oct 2026 | 1,400 |
| Nov 2026 | 1,400 |
Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.
Popular in the same category
tuning_playbook_jaValkyrja3607192A playbook for systematically maximizing the performance of deep learning models.
awesome-bert-japanesehimkt132A list of pre-trained BERT models for Japanese with word/subword tokenization + vocabulary construction algorithm information
japanese-pitch-accent-resourcesolety129Trying to consolidate japanese phonetic, and in particular pitch accent resources into one list
dataset-listikegami-yukino120lists of text corpus and more (mainly Japanese)
GEC-Info-jagotutiyan14Repository for collecting and categorizing Japanese literature on correcting grammar errors.
Resources in similar research fields
llm-jp-4-cookbookllm-jp40Example scripts for LLM-jp-4 modelsShared: Large language models・Tutorials & learning
Gemma2_2b_Japanese_finetuning_colab.ipynbmain12Fine-Tuning Google Gemma for Japanese InstructionsShared: Large language models・Tutorials & learning- japanese-gpt-neox-smallrinna656kA 12‑layer, 768‑hidden Japanese GPT‑NeoX model trained on CC‑100, C4, and Wikipedia, compatible with Huggingface, with an optional toy prefix‑tuning weight that forces each sentence to end with a smiling‑face emoji.HF modelShared: Large language models
- Spark-X2.5-4B-Heretic-jp-ggufsoyaakinohara589kJapanese‑adapted Spark‑X2.5‑4B model (Heretic JP) with refusal attenuation, pretraining, instruction tuning and tool‑calling repair, available in GGUF quantizations from BF16 to Q4_K_M (~2.5 GiB), usable via llama.cpp for 1,048,576‑token context.HF modelShared: Large language models
- llm-jp-4-33b-thinking-ggufllm-jp271kLLM‑jp‑4‑33b‑thinking‑gguf is a 33 B Japanese language model from the National Institute of Informatics, pre‑trained with SFT and DPO (no RL), available for llama.cpp via an LLM‑jp fork, and includes detailed usage instructions in its cookbook.HF modelShared: Large language models
- llm-jp-4.1-8b-thinkingllm-jp80kLLM‑jp‑4.1‑8b‑thinking is a 33 B transformer language model from NII’s LLM R&D Center, pre‑trained with mid‑training only and aligned via SFT/DPO (no RL), designed for Japanese NLP tasks and documented in a cookbook and technical blog.HF modelShared: Large language models