Instructions to use Efficient-Large-Model/NVILA-8B-Video with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Efficient-Large-Model/NVILA-8B-Video with Transformers:

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

pipe = pipeline("text-generation", model="Efficient-Large-Model/NVILA-8B-Video")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Efficient-Large-Model/NVILA-8B-Video", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Efficient-Large-Model/NVILA-8B-Video with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Efficient-Large-Model/NVILA-8B-Video"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Efficient-Large-Model/NVILA-8B-Video",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Efficient-Large-Model/NVILA-8B-Video

SGLang

How to use Efficient-Large-Model/NVILA-8B-Video 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 "Efficient-Large-Model/NVILA-8B-Video" \
    --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": "Efficient-Large-Model/NVILA-8B-Video",
		"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 "Efficient-Large-Model/NVILA-8B-Video" \
        --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": "Efficient-Large-Model/NVILA-8B-Video",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Efficient-Large-Model/NVILA-8B-Video with Docker Model Runner:
```
docker model run hf.co/Efficient-Large-Model/NVILA-8B-Video
```

What is the difference between the nvila 8b base model and video model?

by YoungjaeDev - opened Feb 4, 2025

Discussion

YoungjaeDev

Feb 4, 2025

Please answer...

YoungjaeDev changed discussion title from What is the difference between the nvila 8b base model and others? to What is the difference between the nvila 8b base model and video model? Feb 4, 2025

bfshi

Efficient-Large-Model org Feb 4, 2025

Please refer to the explanation here: https://github.com/NVlabs/VILA/issues/167#issuecomment-2581442972

Thanks!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment