Instructions to use tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF 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 tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF 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 tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M
Use Docker
docker model run hf.co/tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF with Ollama:
ollama run hf.co/tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M
- Unsloth Studio
How to use tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF to start chatting
- Pi
How to use tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- OpenClaw new
How to use tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
- Docker Model Runner
How to use tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF with Docker Model Runner:
docker model run hf.co/tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M
- Lemonade
How to use tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.jp-gijiroku-qwen3-4b-v2-GGUF-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default tokimoa/jp-gijiroku-qwen3-4b-v2-GGUF:Q4_K_M
Run Hermes
hermes
- Atomic Chat
license: apache-2.0
base_model: Qwen/Qwen3-4B-Instruct-2507
language:
- ja
tags:
- gguf
- llama.cpp
- japanese
- meeting-minutes
- gijiroku
jp-gijiroku-qwen3-4b-v2-GGUF
日本語議事録抽出モデル jp-gijiroku-qwen3-4b-v2 のGGUF版です。初代の後継で、実際の60分Zoom会議の録音→話者分離→文字起こし→抽出パイプラインで見つけた弱点を標的に継続学習しました。llama.cppでWindows/Linux/MacのCPU・GPUで動きます。
v2で直したこと(すべて実会議で確認)
- 日付の捏造をしない — 本文に日付がなければ
date: "なし"(初代は不定と明記していた点の解消) - 完了報告を決定事項に混ぜない — 「デプロイは終わってます」は決定でも宿題でもない
- 期限の誤借用をしない — 別の話の「今週中」を無関係なタスクに付けない
- 話者ラベル付き転写に適応 —
話者A: ...形式の生転写を直接入力できる - 報告文の中のコミットを宿題として拾う — 「デプロイできたら結果を共有しておきます」→ todo(担当=発言者)
ファイルと実測(ASR劣化転写20件・全項目正解率)
| ファイル | サイズ | 全項目正解 | 備考 |
|---|---|---|---|
| Q8_0 | 4.0GB | 15/20 | 推奨 |
| Q4_K_M | 2.3GB | 17/20 | 省メモリ |
| f16 | 7.5GB | — | 参照用 |
参考: 初代は同条件でQ8_0 16/20・Q4_K_M 19/20(n=20の揺らぎ圏・同帯域)。v2の価値は上の5項目=実会議で起きる系統的ミスの解消です。整った合成val(50件)は39/50で初代38/50と同等、弱点標的val(60件)は54/60です。
使い方
llama-server -m jp-gijiroku-qwen3-4b-v2-Q8_0.gguf --port 8080 --jinja --reasoning-format none -c 8192
--reasoning-format noneを推奨します。 既定パーサだと判断過程がreasoning_content側に分離されcontentが空になる場合があります- 出力は「判断過程 → 最終行にJSON」です。最終行をパースしてください(スキーマ:
{"date", "attendees", "decisions", "todos": [{"task","owner","due"}], "next_meeting"}) - プロンプトは定型文「次の議事録から出席者・決定事項・宿題(担当と期限)・次回予定を抽出してJSONで出力してください。」+ 本文をそのまま使ってください(学習分布の形式)
- 長時間会議(30分超)は10分前後のチャンクに分けて抽出→統合を推奨します。学習分布(〜2千トークン)に近い入力長のほうが網羅性が大きく上がります(60分実会議で一括=決定1・宿題1に対しチャンク統合=決定7・宿題6)
データと帰属
- 学習データ: 合成会議(正解既知・ASR劣化/話者ラベル/コミットあり・なし対比込み)に対する DeepSeek-V4-Flash の検証済み解答軌跡(利用規約は蒸留を明示的に許可)
- ベース: Qwen/Qwen3-4B-Instruct-2507(Apache-2.0)
Developed by tokimoa — データを外に出さないAI活用を支援しています