Instructions to use ghost613/gemma-ko-2b-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ghost613/gemma-ko-2b-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="ghost613/gemma-ko-2b-AWQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ghost613/gemma-ko-2b-AWQ")
model = AutoModelForCausalLM.from_pretrained("ghost613/gemma-ko-2b-AWQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ghost613/gemma-ko-2b-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ghost613/gemma-ko-2b-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ghost613/gemma-ko-2b-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ghost613/gemma-ko-2b-AWQ

SGLang

How to use ghost613/gemma-ko-2b-AWQ 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 "ghost613/gemma-ko-2b-AWQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ghost613/gemma-ko-2b-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ghost613/gemma-ko-2b-AWQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ghost613/gemma-ko-2b-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ghost613/gemma-ko-2b-AWQ with Docker Model Runner:
```
docker model run hf.co/ghost613/gemma-ko-2b-AWQ
```

Configuration Parsing Warning:In config.json: "quantization_config.modules_to_not_convert" must be an array

Gemma-Ko

Quantized model from: Gemma Ko
Original Gemma Model Page: Gemma

This model card corresponds to the 2B base version of the Gemma-Ko model.

Resources and Technical Documentation:

Terms of Use: Terms

Downloads last month: 5

Safetensors

Model size

3B params

Tensor type

I32

F16

Collection including ghost613/gemma-ko-2b-AWQ

Quantized models

Collection

Models I quantized • 2 items • Updated Jun 4, 2024