Instructions to use heegyu/0716-gemma2-koenzh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use heegyu/0716-gemma2-koenzh with Transformers:

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

pipe = pipeline("text-generation", model="heegyu/0716-gemma2-koenzh")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("heegyu/0716-gemma2-koenzh")
model = AutoModelForCausalLM.from_pretrained("heegyu/0716-gemma2-koenzh")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use heegyu/0716-gemma2-koenzh with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "heegyu/0716-gemma2-koenzh"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "heegyu/0716-gemma2-koenzh",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/heegyu/0716-gemma2-koenzh

SGLang

How to use heegyu/0716-gemma2-koenzh 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 "heegyu/0716-gemma2-koenzh" \
    --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": "heegyu/0716-gemma2-koenzh",
		"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 "heegyu/0716-gemma2-koenzh" \
        --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": "heegyu/0716-gemma2-koenzh",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use heegyu/0716-gemma2-koenzh with Docker Model Runner:
```
docker model run hf.co/heegyu/0716-gemma2-koenzh
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Gemma Chat Template 사용

카테고리: 추론(Reasoning), 싱글 점수 평균: 6.14, 멀티 점수 평균: 3.86
카테고리: 수학(Math), 싱글 점수 평균: 5.29, 멀티 점수 평균: 5.86
카테고리: 글쓰기(Writing), 싱글 점수 평균: 6.71, 멀티 점수 평균: 6.57
카테고리: 코딩(Coding), 싱글 점수 평균: 4.71, 멀티 점수 평균: 6.57
카테고리: 이해(Understanding), 싱글 점수 평균: 8.00, 멀티 점수 평균: 8.71
카테고리: 문법(Grammar), 싱글 점수 평균: 5.14, 멀티 점수 평균: 4.86
전체 싱글 점수 평균: 6.00
전체 멀티 점수 평균: 6.07
전체 점수: 6.04

Downloads last month: 3

Safetensors

Model size

9B params

Tensor type

BF16