Instructions to use FiShota/yamato-3b-v2-legal-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FiShota/yamato-3b-v2-legal-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="FiShota/yamato-3b-v2-legal-gguf",
	filename="yamato_3b_v2.Q3_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use FiShota/yamato-3b-v2-legal-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 FiShota/yamato-3b-v2-legal-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FiShota/yamato-3b-v2-legal-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 FiShota/yamato-3b-v2-legal-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf FiShota/yamato-3b-v2-legal-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 FiShota/yamato-3b-v2-legal-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf FiShota/yamato-3b-v2-legal-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 FiShota/yamato-3b-v2-legal-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FiShota/yamato-3b-v2-legal-gguf:Q4_K_M

Use Docker

docker model run hf.co/FiShota/yamato-3b-v2-legal-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use FiShota/yamato-3b-v2-legal-gguf with Ollama:
```
ollama run hf.co/FiShota/yamato-3b-v2-legal-gguf:Q4_K_M
```

Unsloth Studio

How to use FiShota/yamato-3b-v2-legal-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 FiShota/yamato-3b-v2-legal-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 FiShota/yamato-3b-v2-legal-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FiShota/yamato-3b-v2-legal-gguf to start chatting

How to use FiShota/yamato-3b-v2-legal-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FiShota/yamato-3b-v2-legal-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": "FiShota/yamato-3b-v2-legal-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use FiShota/yamato-3b-v2-legal-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 FiShota/yamato-3b-v2-legal-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 FiShota/yamato-3b-v2-legal-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use FiShota/yamato-3b-v2-legal-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FiShota/yamato-3b-v2-legal-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 "FiShota/yamato-3b-v2-legal-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 FiShota/yamato-3b-v2-legal-gguf with Docker Model Runner:
```
docker model run hf.co/FiShota/yamato-3b-v2-legal-gguf:Q4_K_M
```

Lemonade

How to use FiShota/yamato-3b-v2-legal-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FiShota/yamato-3b-v2-legal-gguf:Q4_K_M

Run and chat with the model

lemonade run user.yamato-3b-v2-legal-gguf-Q4_K_M

List all available models

lemonade list

Yamato-3B-v2 (legal/admin specialist, GGUF)

Sarashina2.2-3B-instruct + QLoRA on 60 hand-crafted legal Q&A samples (v1 50 + v2 10: 民訴 / 行政手続 / 労働契約 / 個人情報 / 不動産登記 / 国保 / 詐欺対処 / 家族財産 / 年金繰下).

Each sample includes plain-language answer + (出典: 法令名第X条) + 弁護士相談 disclaimer.

Variants

Variant	BPW	Size
Q3_K_M	3.91	1.6 GB
Q4_K_M	4.92	2.0 GB
Q5_K_M	5.72	2.3 GB
Q6_K	6.60	2.6 GB
fp16	16.00	6.3 GB

v1 → v2 changes

60 samples (was 50) covering 10 additional legal domains
Same QLoRA recipe (r=16, 3 epochs, lr=2e-4)
Yamato-Bench-ja v0.2 (30 items) compatible

Position

Yamato is the legal/admin specialist sister to HinoMoto (family/keigo). Both share Sarashina2.2-3B base.

Quick start

huggingface-cli download FiShota/yamato-3b-v2-legal-gguf yamato_3b_v2.Q4_K_M.gguf --local-dir .
~/projects/llama.cpp/build_cuda/bin/llama-server -m yamato_3b_v2.Q4_K_M.gguf -c 2048 -ngl 99 --port 8092

Disclaimer

This model provides general legal information for educational purposes. NOT legal advice. Always consult a licensed attorney for individual cases.

License

MIT (inherits from Sarashina2.2-3B-instruct-v0.1).

📈 Rank ablation context (sister models)

This is one variant in a 4-point LoRA rank ablation on the same 60 legal samples:

Variant	LoRA r	Bench %	Notes
v1 / v2	16	46.7%	baseline
v3	32	48.9%	+2.2
v4	64	54.3%	+5.4
v5 ⭐	128	57.6%	+3.3 (current best)

→ All same recipe; only LoRA rank doubled. → Detailed analysis: HinoMoto 開発ノート #9 — "LoRA rank scaling boundary".

Model tree for FiShota/yamato-3b-v2-legal-gguf

Base model

sbintuitions/sarashina2.2-3b

Finetuned

sbintuitions/sarashina2.2-3b-instruct-v0.1

Quantized

(24)

this model

FiShota
/

yamato-3b-v2-legal-gguf

Yamato-3B-v2 (legal/admin specialist, GGUF)

Variants

v1 → v2 changes

Position

Quick start

Disclaimer

License

See also

📈 Rank ablation context (sister models)

See also

Model tree for FiShota/yamato-3b-v2-legal-gguf