Instructions to use AkadashiOmiso/yokiKana-weights with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use AkadashiOmiso/yokiKana-weights with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf AkadashiOmiso/yokiKana-weights:Q8_0 # Run inference directly in the terminal: llama cli -hf AkadashiOmiso/yokiKana-weights:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf AkadashiOmiso/yokiKana-weights:Q8_0 # Run inference directly in the terminal: llama cli -hf AkadashiOmiso/yokiKana-weights:Q8_0
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf AkadashiOmiso/yokiKana-weights:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf AkadashiOmiso/yokiKana-weights:Q8_0
Use Docker
docker model run hf.co/AkadashiOmiso/yokiKana-weights:Q8_0
- Llama new
- LM Studio
- Jan
- Ollama
How to use AkadashiOmiso/yokiKana-weights with Ollama:
ollama run hf.co/AkadashiOmiso/yokiKana-weights:Q8_0
- Unsloth Desktop
- Docker Model Runner
How to use AkadashiOmiso/yokiKana-weights with Docker Model Runner:
docker model run hf.co/AkadashiOmiso/yokiKana-weights:Q8_0
- Lemonade
How to use AkadashiOmiso/yokiKana-weights with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull AkadashiOmiso/yokiKana-weights:Q8_0
Run and chat with the model
lemonade run user.yokiKana-weights-Q8_0
List all available models
lemonade list
- Atomic Chat
yokiKana-weights
yokiKana(Windows の日本語 IME)が使う重みです。配る zip(yokiKana-releases の Releases)には入れず、入れるときにここから取ります。zip の weights.json に、ファイルごとの置き場・SHA256・大きさがあります。
| フォルダ | 中身 | ライセンス |
|---|---|---|
shonagon/charlm5-full-m5-c.bin・charlm7-modern-m5-c.bin |
変換エンジン Shonagon の文字の言語モデル(文語寄り・現代文寄り) | yokiKana のために学習したもの(配る zip と同じ条件で使えます) |
shonagon/onnx128*/ |
Shonagon の CNN(cnn6・cnn10a・cnn10h・jnn11b)。ONNX と埋め込み | 同上 |
chunagon/sarashina2.2-3b-Q8_0.gguf・sarashina2.2-1b-Q8_0.gguf |
誤字指摘 Chunagon の LLM。sbintuitions/sarashina2.2-3b・sarashina2.2-1b を llama.cpp で Q8_0 に量子化したもの | MIT |
chunagon/sudachidict-core-20260723.1/system_core.dic |
誤字指摘 Chunagon が「癖?」で語を分けるときに使う Sudachi の辞書(SudachiDict core。WorksApplications/SudachiDict) | Apache-2.0 |
ファイルの名前は変えません。中身が変わるときは新しいコミットになり、zip の weights.json が revision と SHA256 で指します。
- Downloads last month
- 93
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support