Instructions to use ruiname/ruiname-AI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ruiname/ruiname-AI 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 ruiname/ruiname-AI:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ruiname/ruiname-AI:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ruiname/ruiname-AI:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ruiname/ruiname-AI:Q4_K_M

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 ruiname/ruiname-AI:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf ruiname/ruiname-AI:Q4_K_M

Use Docker

docker model run hf.co/ruiname/ruiname-AI:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use ruiname/ruiname-AI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ruiname/ruiname-AI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ruiname/ruiname-AI",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ruiname/ruiname-AI:Q4_K_M

Ollama
How to use ruiname/ruiname-AI with Ollama:
```
ollama run hf.co/ruiname/ruiname-AI:Q4_K_M
```
Unsloth Desktop

How to use ruiname/ruiname-AI with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ruiname/ruiname-AI:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ruiname/ruiname-AI:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ruiname/ruiname-AI with Docker Model Runner:
```
docker model run hf.co/ruiname/ruiname-AI:Q4_K_M
```

Lemonade

How to use ruiname/ruiname-AI with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ruiname/ruiname-AI:Q4_K_M

Run and chat with the model

lemonade run user.ruiname-AI-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ruiname/ruiname-AI with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ruiname/ruiname-AI: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 ruiname/ruiname-AI:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ruiname/ruiname-AI with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ruiname/ruiname-AI: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 "ruiname/ruiname-AI: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"

ruiname-AI

Rui の LINE での話し方を真似するチャットモデルです。 LiquidAI/LFM2.5-1.2B-JP-202606 をフルファインチューニングしています。

学習データ（会話履歴）は非公開で、このリポジトリには含まれていません。

ファイル

ファイル	形式	サイズ	用途
`ruiname-AI-Q4_K_M.gguf`	GGUF 4bit	0.8 GB	LM Studio / Ollama / llama.cpp（普段使い）
`ruiname-AI-Q8_0.gguf`	GGUF 8bit	1.4 GB	高品質版
`model.safetensors` ほか	Transformers (bf16)	2.6 GB	再学習・再量子化用

使い方

システムプロンプトは学習時と同じものを使ってください。

あなたはRui（鈴木類）です。友達や家族とLINEで話しているときと同じ口調・テンポで返信してください。短いメッセージを何通かに分けて送ることが多く、改行は別の吹き出しを表します。

推奨パラメータ: temperature 0.7, min_p 0.1, repeat_penalty 1.05

llama-cli -m ruiname-AI-Q4_K_M.gguf -cnv -sys "<上のシステムプロンプト>" --temp 0.7 --min-p 0.1

学習

損失は Rui の発言部分のみ
2 エポック、lr 2e-5（cosine）、検証損失が最小の 1 エポック目を採用（6.46 → 2.97）
A100 1 枚で約 2 分

Downloads last month: 402

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for ruiname/ruiname-AI

Base model

LiquidAI/LFM2.5-1.2B-Base

Finetuned

LiquidAI/LFM2.5-1.2B-JP-202606

Quantized

(12)

this model

Quantizations

1 model