Instructions to use QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF", dtype="auto")

llama-cpp-python

How to use QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF",
	filename="EZO-gemma-2-2b-jpn-it.Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/EZO-gemma-2-2b-jpn-it-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 QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/EZO-gemma-2-2b-jpn-it-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 QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/EZO-gemma-2-2b-jpn-it-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 QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/EZO-gemma-2-2b-jpn-it-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": "QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF:Q4_K_M

SGLang

How to use QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF:Q4_K_M
```

Unsloth Studio

How to use QuantFactory/EZO-gemma-2-2b-jpn-it-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 QuantFactory/EZO-gemma-2-2b-jpn-it-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 QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.EZO-gemma-2-2b-jpn-it-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF

This is quantized version of AXCXEPT/EZO-gemma-2-2b-jpn-it created using llama.cpp

Original Model Card

[AXCXEPT/EZO-gemma-2-2b-jpn-it]

[Model Information]

This model is based on google/gemma-2-2b-jpn-it, enhanced with multiple tuning techniques to improve its general performance. While it excels in Japanese language tasks, it's designed to meet diverse needs globally.

google/gemma-2-2b-jpn-itをベースとして、複数のチューニング手法を採用のうえ、汎用的に性能を向上させたモデルです。日本語タスクに優れつつ、世界中の多様なニーズに応える設計となっています。

[Benchmark Results]

Terms of Use: Terms

This model is based on google/gemma-2-2b-jpn-it and is subject to the Gemma Terms of Use. For detailed information, please refer to the official Gemma license page.

このモデルはgoogle/gemma-2-2b-jpn-itをベースにしており、Gemmaの利用規約に従います。詳細については、Gemmaの公式ライセンスページをご参照ください。

[Usage]

Here are some code snippets to quickly get started with the model. First, run: pip install -U transformers accelerate Then, copy the snippet from the relevant section for your use case.

以下に、モデルの実行を素早く開始するためのコードスニペットをいくつか紹介します。まず、 pip install -U transformers を実行し、使用例に関連するセクションのスニペットをコピーしてください。

[Chat Template]

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "AXCXEPT/EZO-gemma-2-2b-jpn-it"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
)

messages = [
    {"role": "user", "content": f"""
以下の記事から日付をすべて抽出せよ。
あすから今冬一番の寒波 “10年に一度の低温に” 大雪に備えを

この冬一番の非常に強い寒気が流れ込むため、24日から北日本から西日本の日本海側で大雪や猛吹雪となるほか、ふだん雪の少ない太平洋側の平地でも大雪となるおそれがあります。
全国的に10年に一度程度の低い気温になる見込みで、路面や水道管の凍結による被害が出るおそれもあります。予定の変更を検討するなど、大雪や低温への備えを進めてください。

気象庁によりますと、日本付近は24日から26日 木曜日ごろにかけて冬型の気圧配置が強まり、北日本から西日本の上空には、この冬一番の非常に強い寒気が流れ込む見込みです。

このため、北日本から西日本の日本海側を中心に大雪や猛吹雪となり、短時間で積雪が急激に増えるおそれがあります。
"""},
]
input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True).to("cuda")

outputs = model.generate(**input_ids, max_new_tokens=512)
print(tokenizer.decode(outputs[0]))

[Template]

<bos><start_of_turn>user
Write a hello world program<end_of_turn>
<start_of_turn>model
XXXXXX<end_of_turn><eos>

[Model Data]

Training Dataset]

We extracted high-quality data from Japanese Wikipedia and FineWeb to create instruction data. Our innovative training approach allows for performance improvements across various languages and domains, making the model suitable for global use despite its focus on Japanese data.

日本語のWikiデータおよび、FineWebから良質なデータのみを抽出し、Instructionデータを作成しました。このモデルでは日本語に特化させていますが、世界中のどんなユースケースでも利用可能なアプローチです。

https://huggingface.co/datasets/legacy-datasets/wikipedia https://huggingface.co/datasets/HuggingFaceFW/fineweb

Data Preprocessing

We used a plain instruction tuning method to train the model on exemplary responses. This approach enhances the model's ability to understand and generate high-quality responses across various languages and contexts.

プレインストラクトチューニング手法を用いて、模範的回答を学習させました。この手法により、モデルは様々な言語やコンテキストにおいて高品質な応答を理解し生成する能力が向上しています。

Implementation Information

[Pre-Instruction Training]

https://huggingface.co/instruction-pretrain/instruction-synthesizer

[Disclaimer]

このモデルは研究開発のみを目的として提供されるものであり、実験的なプロトタイプとみなされるべきモデルです。商業的な使用やミッションクリティカルな環境への配備を意図したものではありません。本モデルの使用は、使用者の責任において行われるものとし、その性能および結果は保証されません。 Axcxept株式会社は、直接的、間接的、特別、偶発的、結果的な損害、または本モデルの使用から生じるいかなる損失に対しても、得られた結果にかかわらず、一切の責任を負いません。利用者は、本モデルの使用に伴うリスクを十分に理解し、自己の判断で使用するものとします。

[Hardware]

A100 × 8(Running in 2h)

[謝辞]

本ベースモデルを開発してくださったGoogle社ならびに当該チームの開発者の方々、また自動評価の手法を提供してくださった多数の方々に感謝と尊敬の意を表します。

[We are.]

Downloads last month: 103

GGUF

Model size

3B params

Architecture

gemma2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Model tree for QuantFactory/EZO-gemma-2-2b-jpn-it-GGUF

Base model

google/gemma-2-2b

Finetuned

google/gemma-2-2b-it

Finetuned

google/gemma-2-2b-jpn-it

Quantized

(23)

this model