Instructions to use melonTraining/gemma-4-31b-kairos with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use melonTraining/gemma-4-31b-kairos with PEFT:
```
Task type is invalid.
```

How to use melonTraining/gemma-4-31b-kairos with Transformers:

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

pipe = pipeline("text-generation", model="melonTraining/gemma-4-31b-kairos")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("melonTraining/gemma-4-31b-kairos")
model = AutoModelForMultimodalLM.from_pretrained("melonTraining/gemma-4-31b-kairos")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use melonTraining/gemma-4-31b-kairos with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "melonTraining/gemma-4-31b-kairos"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "melonTraining/gemma-4-31b-kairos",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/melonTraining/gemma-4-31b-kairos

SGLang

How to use melonTraining/gemma-4-31b-kairos 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 "melonTraining/gemma-4-31b-kairos" \
    --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": "melonTraining/gemma-4-31b-kairos",
		"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 "melonTraining/gemma-4-31b-kairos" \
        --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": "melonTraining/gemma-4-31b-kairos",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use melonTraining/gemma-4-31b-kairos with Docker Model Runner:
```
docker model run hf.co/melonTraining/gemma-4-31b-kairos
```

gemma-4-31b-kairos / optimizer.bin

galeswel

Add files using upload-large-folder tool

7deec60 verified 2 days ago

Download

History Blame Contribute Delete

15.7 GB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 5a673fa4794dc706564a640084efe4bbdef321acb05c6a16b0d77de0d80655eb
Size of remote file:: 15.7 GB
SHA256:: 71c3f8c8daa01800c3b88704ff48619b7472f4beaa9a643d95fd59362e0453f9

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.