Instructions to use posterllava/posterllava_v0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use posterllava/posterllava_v0 with Transformers:

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

pipe = pipeline("text-generation", model="posterllava/posterllava_v0")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("posterllava/posterllava_v0")
model = AutoModelForCausalLM.from_pretrained("posterllava/posterllava_v0")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use posterllava/posterllava_v0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "posterllava/posterllava_v0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "posterllava/posterllava_v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/posterllava/posterllava_v0

SGLang

How to use posterllava/posterllava_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 "posterllava/posterllava_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": "posterllava/posterllava_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 "posterllava/posterllava_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": "posterllava/posterllava_v0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use posterllava/posterllava_v0 with Docker Model Runner:
```
docker model run hf.co/posterllava/posterllava_v0
```

PosterLLaVA Model Card

Model details

Model type: PoserLLaVA is an layout generation model with LLaVa achitecture. The current model is fine-tuned with the LLaVA-v1.5-13B checkpoint.

Model date: posterllava_v0 was trained in March 2024.

Training dataset

7k banner layouts from Ad Banner dataset
60k commerical poster layouts from CGL dataset and PosterLayout with text constraints
4k social media poster layouts from QB-Poster dataset

Evaluation dataset

the combination of the corresponding test sets of the above training datasets

Downloads last month: 14

posterllava
/

posterllava_v0

PosterLLaVA Model Card

Model details

Training dataset

Evaluation dataset

Spaces using posterllava/posterllava_v0 2