Instructions to use AXCXEPT/EZO2.5-gemma-3-12b-it-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AXCXEPT/EZO2.5-gemma-3-12b-it-Preview with Transformers:

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

pipe = pipeline("image-text-to-text", model="AXCXEPT/EZO2.5-gemma-3-12b-it-Preview")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("AXCXEPT/EZO2.5-gemma-3-12b-it-Preview")
model = AutoModelForMultimodalLM.from_pretrained("AXCXEPT/EZO2.5-gemma-3-12b-it-Preview", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AXCXEPT/EZO2.5-gemma-3-12b-it-Preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AXCXEPT/EZO2.5-gemma-3-12b-it-Preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AXCXEPT/EZO2.5-gemma-3-12b-it-Preview",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/AXCXEPT/EZO2.5-gemma-3-12b-it-Preview

SGLang

How to use AXCXEPT/EZO2.5-gemma-3-12b-it-Preview 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 "AXCXEPT/EZO2.5-gemma-3-12b-it-Preview" \
    --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": "AXCXEPT/EZO2.5-gemma-3-12b-it-Preview",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "AXCXEPT/EZO2.5-gemma-3-12b-it-Preview" \
        --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": "AXCXEPT/EZO2.5-gemma-3-12b-it-Preview",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use AXCXEPT/EZO2.5-gemma-3-12b-it-Preview with Docker Model Runner:
```
docker model run hf.co/AXCXEPT/EZO2.5-gemma-3-12b-it-Preview
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

AXCXEPT/EZO2.5-gemma-3-12b-it-Preview

Model Details

昨今登場したLLM自身の力を自力で向上させる「GRPO」や「PPO」の概念を、弊社で開発した「EZO」というトレーニング手法にミックスすることで、 3,000件のデータセット、2時間×H200×8台のトレーニングで、Japanese MT Benchおよび、Elyza Tasks100におけるベースモデルの日本語性能を向上させることに成功したモデルです。

本トレーニング手法は、まだ研究段階にあり手法の自動化や、アブレーションが必要なステータスではあるものの、複雑かつ非常に時間がかかるGRPO/PPOといった強化学習方法を、低予算でも実現できる大体の手段となりえると考えています。

By integrating the recently introduced concepts of “GRPO” and “PPO” — which enable LLMs to autonomously improve their own capabilities — into our proprietary training method “EZO,” we successfully enhanced the Japanese performance of the base model on both Japanese MT Bench and Elyza Tasks100. This was achieved using only 3,000 training samples and two hours of training on 8 H200 GPUs. While this training method is still in the research phase and requires further automation and ablation studies, we believe it represents a viable alternative to complex and time-consuming reinforcement learning approaches like GRPO/PPO — making it achievable even on a limited budget.

Bench Mark

もともと非常に高い日本語性能を示していた、google/gemma-3-12b-itから、短時間のトレーニングで性能向上を達成。 32B, 72Bのモデルにも一部肉薄し、ベースモデルの性能向上に伴い特化型の性能向上が実現できている。 ※ただし、ベンチマークそのものの多様性が今後必要となるため、今後は、選択肢の多い英語での実施も行い、トレーニング成果の実用性実証研究を行う予定です。

How to use

Runs on a single A40 GPU.

vllm serve AXCXEPT/EZO2.5-gemma-3-12b-it-Preview --max-model-len 32768 --enforce-eager

from openai import OpenAI
client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="token-abc123",
)

prompt = """Every morning Aya goes for a $9$-kilometer-long walk and stops at a coffee shop afterwards. When she walks at a constant speed of $s$ kilometers per hour, the walk takes her 4 hours, including $t$ minutes spent in the coffee shop. When she walks $s+2$ kilometers per hour, the walk takes her 2 hours and 24 minutes, including $t$ minutes spent in the coffee shop. Suppose Aya walks at $s+rac{1}{2}$ kilometers per hour. Find the number of minutes the walk takes her, including the $t$ minutes spent in the coffee shop."""
completion = client.chat.completions.create(
  model="AXCXEPT/EZO2.5-gemma-3-12b-it-Preview",
  messages=[
    {"role": "user", "content": prompt}
  ],
  temperature=0.0,
  top_p=1.0,
  max_tokens: 20480
)

print(completion.choices[0].message)

ベンチマークスコアは、temperature: 0.0、top_p: 1.0、"max_tokens": 20480で推論した結果に基づきます。Cons@64などのばらつきによる評価は未実施です。

License

このモデルは研究のために開発されています。利用に際する一切の損害に関して、当社ならびに開発者は一切持たないことを理解の上ご活用ください。 Of course. Here's the English translation:

This model has been developed for research purposes. Please use it with the understanding that our company and the developers accept no responsibility for any damages resulting from its use.

Special Thanks

本モデルのベースモデルの開発を行った、Google社ならびに同社の開発チームに、尊敬と敬意の念をここに表します。 We would like to express our sincere respect and appreciation to Google and its development team for creating the base model upon which this model is built.