Instructions to use Stanford-ILIAD/minivla-libero90-prismatic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Stanford-ILIAD/minivla-libero90-prismatic with Transformers:

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

pipe = pipeline("image-text-to-text", model="Stanford-ILIAD/minivla-libero90-prismatic")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Stanford-ILIAD/minivla-libero90-prismatic", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Stanford-ILIAD/minivla-libero90-prismatic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Stanford-ILIAD/minivla-libero90-prismatic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Stanford-ILIAD/minivla-libero90-prismatic",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Stanford-ILIAD/minivla-libero90-prismatic

SGLang

How to use Stanford-ILIAD/minivla-libero90-prismatic 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 "Stanford-ILIAD/minivla-libero90-prismatic" \
    --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": "Stanford-ILIAD/minivla-libero90-prismatic",
		"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 "Stanford-ILIAD/minivla-libero90-prismatic" \
        --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": "Stanford-ILIAD/minivla-libero90-prismatic",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Stanford-ILIAD/minivla-libero90-prismatic with Docker Model Runner:
```
docker model run hf.co/Stanford-ILIAD/minivla-libero90-prismatic
```

MiniVLA 1B (Prismatic-Compatible Version)

This checkpoint is in a format that is compatible with the training script from the original Prismatic VLMs project codebase, which the OpenVLA team built on top of to develop the OpenVLA model.

This Prismatic-compatible checkpoint may be useful if you wish to fully fine-tune MiniVLA (all 1 billion parameters) via native PyTorch Fully Sharded Data Parallel (FSDP) using the Prismatic VLMs training script. If you instead wish to do Parameter-Efficient Fine-Tuning via LoRA, you can use the MiniVLA checkpoint linked above, which is compatible with the Hugging Face transformers library. We recommend fine-tuning via LoRA if you do not have sufficient compute to fully fine-tune a 1B-parameter model (e.g., multiple A100/H100 GPUs).

Usage Instructions

See the MiniVLA GitHub README for instructions on how to use this checkpoint for full fine-tuning.

Citation

BibTeX:

@article{belkhale24minivla,
    title={MiniVLA: A Better VLA with a Smaller Footprint},
    author={Suneel Belkhale and Dorsa Sadigh},
    url={https://github.com/Stanford-ILIAD/openvla-mini}
    year={2024}
}

Downloads last month: 95

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including Stanford-ILIAD/minivla-libero90-prismatic

MiniVLA

Collection

Models for MiniVLA architecture • 5 items • Updated Dec 12, 2024 • 4