Instructions to use qnguyen3/nanoLLaVA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qnguyen3/nanoLLaVA with Transformers:

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

pipe = pipeline("text-generation", model="qnguyen3/nanoLLaVA", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("qnguyen3/nanoLLaVA", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use qnguyen3/nanoLLaVA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qnguyen3/nanoLLaVA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qnguyen3/nanoLLaVA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/qnguyen3/nanoLLaVA

SGLang

How to use qnguyen3/nanoLLaVA 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 "qnguyen3/nanoLLaVA" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qnguyen3/nanoLLaVA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "qnguyen3/nanoLLaVA" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qnguyen3/nanoLLaVA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use qnguyen3/nanoLLaVA with Docker Model Runner:
```
docker model run hf.co/qnguyen3/nanoLLaVA
```

CUDA out of memory without Gradio

by snakelemma - opened May 16, 2024

Discussion

snakelemma

May 16, 2024

I can run the model locally through Gradio, but not standalone. For Gradio I use the code from https://huggingface.co/spaces/qnguyen3/nanoLLaVA.
The standalone version (using the sample code) gives me "CUDA out of memory" with NVIDIA GeForce RTX 4050 6Gb, while through Gradio the memory is not filled.
The error is thrown when SigLipAttention is loaded. Any idea why less vram is used with Gradio?

snakelemma changed discussion title from CUDA out of memory without using Gradio to CUDA out of memory without Gradio May 16, 2024

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