Instructions to use FiShota/yamato-3b-v5-r128-legal-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FiShota/yamato-3b-v5-r128-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-v5-r128-legal-gguf",
	filename="yamato_3b_v5_r128.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-v5-r128-legal-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf FiShota/yamato-3b-v5-r128-legal-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf FiShota/yamato-3b-v5-r128-legal-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf FiShota/yamato-3b-v5-r128-legal-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf FiShota/yamato-3b-v5-r128-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-v5-r128-legal-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf FiShota/yamato-3b-v5-r128-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-v5-r128-legal-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FiShota/yamato-3b-v5-r128-legal-gguf:Q4_K_M

Use Docker

docker model run hf.co/FiShota/yamato-3b-v5-r128-legal-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use FiShota/yamato-3b-v5-r128-legal-gguf with Ollama:
```
ollama run hf.co/FiShota/yamato-3b-v5-r128-legal-gguf:Q4_K_M
```

Unsloth Studio

How to use FiShota/yamato-3b-v5-r128-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-v5-r128-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-v5-r128-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-v5-r128-legal-gguf to start chatting

How to use FiShota/yamato-3b-v5-r128-legal-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf FiShota/yamato-3b-v5-r128-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-v5-r128-legal-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use FiShota/yamato-3b-v5-r128-legal-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf FiShota/yamato-3b-v5-r128-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-v5-r128-legal-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use FiShota/yamato-3b-v5-r128-legal-gguf with Docker Model Runner:
```
docker model run hf.co/FiShota/yamato-3b-v5-r128-legal-gguf:Q4_K_M
```

Lemonade

How to use FiShota/yamato-3b-v5-r128-legal-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FiShota/yamato-3b-v5-r128-legal-gguf:Q4_K_M

Run and chat with the model

lemonade run user.yamato-3b-v5-r128-legal-gguf-Q4_K_M

List all available models

lemonade list

Yamato-3B-v5 (r=128) — Best legal/admin specialist

About the developer — One person (FiShota) building a Japanese LM stack from scratch on a single RTX 3090. Yamato is the legal/admin SFT specialist in the family. See HinoMoto-100M v15 for the from-scratch line, and hinomoto-bench-ja for the cultural-axis benchmark. GitHub · X

Best-performing variant in the rank ablation series:

Variant	LoRA r	Overall	New domain	avg_len
v1	16	46.7%	43.3%	612 c
v3	32	48.9%	43.3%	501 c
v4	64	54.3%	53.3%	415 c
v5 ⭐	128	57.6%	50.0%	482 c

Same 60 hand-crafted legal Q&A samples. Only LoRA rank doubled. At small-domain SFT scale, rank capacity scales much further than commonly assumed (PEFT tutorials default to r=8/16). Per-doubling deltas: +2.2 / +5.4 / +3.3.

Why this monotonic gain is interesting

In a sister experiment (HinoMoto multi-axis SFT, 452 samples × 4 axes ≈ 113 per axis), the same recipe at r=64 regressed by -4pt versus r=16 (96.0% → 92.0%).

→ rank scaling is bounded by samples-per-axis, not total samples.

Yamato (60 / 1 = 60 per axis): under-fit at any rank, so r=128 still helps.
HinoMoto SFT (452 / 4 = 113 per axis): saturated by r=16, larger r overfits.

Crossover threshold for 3B + LoRA: ~100 samples/axis (empirical, single-base observation).

→ Detailed analysis: HinoMoto 開発ノート #9 (note.com / GitHub).

Bench setup

30 items in HinoMoto-Bench-ja yamato_legal_v02.jsonl (民法 / 刑法 / 行政手続 / 労契 / 個人情報 / 不動産登記 / 国保 / 詐欺 / 家族財産 / 年金等)
Pass criteria: must contain expected legal references (条文番号 / 法令名) + must NOT match anti-pattern (一律無効 / 必ず勝てます等)
3-seed sampling for stochastic noise

Quants

This repo includes Q3_K_M / Q4_K_M / Q5_K_M / Q6_K plus fp16. Q4_K_M recommended for general use; deployment task may benefit from per-task selection (see HinoMoto 開発ノート #8 on quantization non-monotonicity).

License

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

Model tree for FiShota/yamato-3b-v5-r128-legal-gguf

Base model

sbintuitions/sarashina2.2-3b

Finetuned

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

Quantized

(24)

this model