# SakuraLLM/SakuraLLM

适配轻小说/Galgame的日中翻译大模型

Repository: https://github.com/SakuraLLM/SakuraLLM
Canonical: https://ross.abutalabs.com/products/sakurallm
Language: Python
License: GPL-3.0
License Family: copyleft
Last push: 2026-07-23T09:18:37+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 94, release rhythm 8, longevity 79
- inputs: {"age_days": 1106, "days_push": 41, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4735, forks 118 (observed 2026-08-28T04:08:57.740769+00:00)

## What it is
SakuraLLM is a series of fine-tuned open large language models for Japanese-to-Chinese translation specialized in light novel and Galgame (ACGN) text. The repository provides model weights in GGUF format, prompt format documentation, and usage guides for offline self-hosted inference.

## Use cases
- translate japanese light novels to chinese
- translate galgame dialogue with an offline model
- self-host a japanese-chinese translation llm
- translate visual novel text preserving character names
- run a translation model locally with gguf
- translate game scripts with a glossary for consistent terms

## When to choose
- you need ACGN-style Japanese-to-Chinese translation with controllable, offline deployment
- you want open weights you can run locally via llama.cpp/GGUF
- you need glossary support to keep proper nouns and pronouns consistent

## When to avoid
- you need commercial use - models are CC BY-NC-SA and non-commercial only
- you need translation between other language pairs
- you want a turnkey translation app rather than model weights and prompt docs

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, nlp, machine-learning
- domain: large-language-models
- platform: python, self-hosted
- tags: translation, japanese-to-chinese, light-novel, galgame, gguf, fine-tuned-models, acgn, natural-language-processing, localization, gpu

## Member repositories
- SakuraLLM/SakuraLLM (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:57.740769+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:18:59.999721+00:00, confidence not recorded.
  - readme: https://github.com/SakuraLLM/SakuraLLM (fetched 2026-08-28T04:08:57.740769+00:00, sha cf23332f3ef0)
- Data as of 2026-08-30T08:39:29.467469+00:00.