Instructions to use trashpanda-org/gemma-4-31b-larkspur-v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trashpanda-org/gemma-4-31b-larkspur-v0 with Transformers:

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

pipe = pipeline("image-text-to-text", model="trashpanda-org/gemma-4-31b-larkspur-v0")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("trashpanda-org/gemma-4-31b-larkspur-v0")
model = AutoModelForMultimodalLM.from_pretrained("trashpanda-org/gemma-4-31b-larkspur-v0")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use trashpanda-org/gemma-4-31b-larkspur-v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trashpanda-org/gemma-4-31b-larkspur-v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "trashpanda-org/gemma-4-31b-larkspur-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/trashpanda-org/gemma-4-31b-larkspur-v0

SGLang

How to use trashpanda-org/gemma-4-31b-larkspur-v0 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 "trashpanda-org/gemma-4-31b-larkspur-v0" \
    --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": "trashpanda-org/gemma-4-31b-larkspur-v0",
		"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 "trashpanda-org/gemma-4-31b-larkspur-v0" \
        --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": "trashpanda-org/gemma-4-31b-larkspur-v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use trashpanda-org/gemma-4-31b-larkspur-v0 with Docker Model Runner:
```
docker model run hf.co/trashpanda-org/gemma-4-31b-larkspur-v0
```

gemma-4-31b-larkspur-v0 / model-00002-of-00002.safetensors

Hasnonname

Upload merged Gemma 4 31B QLoRA finetune (larkspur-v0)

66113d8 verified about 2 months ago

Download

History Blame Contribute Delete

12.8 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:: c364250a3e1553a2f5d4f60c9fa5eacef503951bbd3bcf0c394259ca48404115
Size of remote file:: 12.8 GB
SHA256:: 4292d9d36f8b703b7528f0f3f48662e10f8ca588912b5b7cb0fe0c7d170e34e9

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