
This repository contains the code for supervised fine-tuning of LLM-jp models.
Description in other languages
Statistics
Statistics as of Nov 17, 2026
GitHub stars
66
+1 (Oct 13〜)
Last commit
Jun 2024
Created on GitHub
Oct 11, 2023
Listed
Oct 23, 2023
Stars over time
Show as a table
| Month | Stars |
|---|---|
| Dec 2025 | 62 |
| Jan 2026 | 62 |
| Feb 2026 | 62 |
| Mar 2026 | 62 |
| Apr 2026 | 62 |
| May 2026 | 62 |
| Jun 2026 | 62 |
| Jul 2026 | 62 |
| Aug 2026 | 62 |
| Sep 2026 | 63 |
| Oct 2026 | 65 |
| Nov 2026 | 66 |
Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.
Popular in the same category
llm-lora-classificationhppRC97llm-lora-classification
llm-jp-tokenizerllm-jp54This is a repository that summarizes the tokenizer related to LLM being developed at the LLM Study Group (LLM-jp).
japanese-llm-rankingyuzu-ai50This repository supports YuzuAI's Rakuda leaderboard of Japanese LLMs, which is a Japanese-focused analogue of LMSYS' Vicuna eval.
japanese-llm-roleplay-benchmarkoshizo42This repository was created to evaluate the performance of character role-playing in Japanese LLM.
jmlm_scoringminhpqn5Masked Language Model-based Scoring for Japanese and Vietnamese
t5_japanese_dialogue_generationJinyamyzk3Conversation generation using T5.
Resources in similar research fields
- deberta-v3-base-japaneseku-nlp13kJapanese DeBERTa V3 base pre‑trained on 540 B tokens from LLM‑jp v1.0, trained with a modified DeBERTa V3 setup, uses a unigram byte‑fallback tokenizer (no morphological analyzer), and is fine‑tuned for JGLUE NLU tasks.HF modelShared: Language Models・Semantic Text Processing
gpt2-japanesetanreinama322Japanese GPT2 Generation ModelShared: Language Models・Semantic Text Processing
t5-japanesemegagonlabs39Codes to pre-train Japanese T5 modelsShared: Language Models・Semantic Text Processing- 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: Language Models・Semantic Text Processing
- llm-jp-3-150mllm-jp75kLLM‑jp‑3‑150m—a 150‑M‑parameter Japanese language model from the National Institute of Informatics’ LLM R&D Center—is distributed in Hugging Face Transformers format, requiring torch ≥ 2.3.0, transformers ≥ 4.40.1, accelerate ≥ 0.29.3, flash‑attn ≥ 2.5.8, and was pretrained on Japanese Wikipedia, Common Crawl, WARP/PDF, WARP/HTML, and Kaken data using a unigram byte‑fallback tokenizer.HF modelShared: Language Models・Semantic Text Processing
- modernbert-ja-310msbintuitions36kModernBERT‑Ja‑310M is a Japanese‑language BERT variant that blends local‑global attention with RoPE, trained on 4.09 T tokens of Japanese/English text, supports a 102 400‑word vocabulary, 8 192‑token sequences, and is optimized for Flash Attention 2.HF modelShared: Language Models・Semantic Text Processing