Instructions to use kawasumi/Tema_Q-R12.2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kawasumi/Tema_Q-R12.2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="kawasumi/Tema_Q-R12.2-GGUF",
	filename="Tema_Q-R12.2-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use kawasumi/Tema_Q-R12.2-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf kawasumi/Tema_Q-R12.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf kawasumi/Tema_Q-R12.2-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 kawasumi/Tema_Q-R12.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf kawasumi/Tema_Q-R12.2-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 kawasumi/Tema_Q-R12.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf kawasumi/Tema_Q-R12.2-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 kawasumi/Tema_Q-R12.2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kawasumi/Tema_Q-R12.2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/kawasumi/Tema_Q-R12.2-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use kawasumi/Tema_Q-R12.2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kawasumi/Tema_Q-R12.2-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kawasumi/Tema_Q-R12.2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kawasumi/Tema_Q-R12.2-GGUF:Q4_K_M

Ollama
How to use kawasumi/Tema_Q-R12.2-GGUF with Ollama:
```
ollama run hf.co/kawasumi/Tema_Q-R12.2-GGUF:Q4_K_M
```

Unsloth Studio new

How to use kawasumi/Tema_Q-R12.2-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 kawasumi/Tema_Q-R12.2-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 kawasumi/Tema_Q-R12.2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kawasumi/Tema_Q-R12.2-GGUF to start chatting

Docker Model Runner
How to use kawasumi/Tema_Q-R12.2-GGUF with Docker Model Runner:
```
docker model run hf.co/kawasumi/Tema_Q-R12.2-GGUF:Q4_K_M
```

Lemonade

How to use kawasumi/Tema_Q-R12.2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kawasumi/Tema_Q-R12.2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Tema_Q-R12.2-GGUF-Q4_K_M

List all available models

lemonade list

🚀 Tema_Q-R12.2

🔥 モデル概要

Tema_Q-R12.2（天馬求） は、Googleが開発した高性能なオープンモデル Gemma 2 9B を基盤にした、日本語、英語向けの改良版大規模言語モデル（LLM）です。

通常のGemma 2では回答が難しいプロンプトに対しても、より自由で有用な応答を生成できるよう設計されています。クリエイティブな執筆、複雑なプログラミングタスク、ディープな知識探求など、あらゆる分野でAIの可能性を最大限に引き出したいユーザーに最適です。このモデルは非情に強力な推論体系を取ります。

Tema_Q-R12.2 is an improved Large Language Model (LLM) tailored for Japanese, English, and Chinese, built upon Gemma 2 9B, a high-performance open model developed by Google.

It is designed to generate more flexible and useful responses, even for prompts that the standard Gemma 2 might find challenging to answer. It is ideal for users who wish to maximize the potential of AI in all fields, including creative writing, complex programming tasks, and deep knowledge exploration.

項目	詳細
ベースモデル	Google Gemma 2 9B
モデル名	Tema_Q-R12.2
対応言語	日本語 (JA), 英語 (EN)
モデルサイズ	9 Billion Parameters
ライセンス	Gemma 2のライセンスに準拠
開発	KY, TY, HY, KK

🛡️ 責任あるAI利用と学習データの安全性

⚠️ 責任ある利用の徹底

ユーザーの責任: モデルの利用者は、生成されたコンテンツが、適用される法律、規制、およびHugging Faceの利用規約/コンテンツポリシーに準拠することを全面的に保証する必要があります。
禁止事項: このモデルを、いかなる差別、ハラスメント、暴力、違法行為、および有害な目的のために利用することを固く禁じます。

Downloads last month: 11

GGUF

Model size

9B params

Architecture

gemma2

Hardware compatibility

4-bit

Model tree for kawasumi/Tema_Q-R12.2-GGUF

Base model

google/gemma-2-9b

Finetuned

google/gemma-2-9b-it

Finetuned

kawasumi/Tema_Q-R12.2

Quantized

(3)

this model