Instructions to use shikiw/LLaVA-v1.5-MoCa-7B-pretrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shikiw/LLaVA-v1.5-MoCa-7B-pretrain with Transformers:

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

pipe = pipeline("image-text-to-text", model="shikiw/LLaVA-v1.5-MoCa-7B-pretrain")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shikiw/LLaVA-v1.5-MoCa-7B-pretrain")
model = AutoModelForCausalLM.from_pretrained("shikiw/LLaVA-v1.5-MoCa-7B-pretrain")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use shikiw/LLaVA-v1.5-MoCa-7B-pretrain with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shikiw/LLaVA-v1.5-MoCa-7B-pretrain"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shikiw/LLaVA-v1.5-MoCa-7B-pretrain",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/shikiw/LLaVA-v1.5-MoCa-7B-pretrain

SGLang

How to use shikiw/LLaVA-v1.5-MoCa-7B-pretrain 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 "shikiw/LLaVA-v1.5-MoCa-7B-pretrain" \
    --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": "shikiw/LLaVA-v1.5-MoCa-7B-pretrain",
		"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 "shikiw/LLaVA-v1.5-MoCa-7B-pretrain" \
        --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": "shikiw/LLaVA-v1.5-MoCa-7B-pretrain",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use shikiw/LLaVA-v1.5-MoCa-7B-pretrain with Docker Model Runner:
```
docker model run hf.co/shikiw/LLaVA-v1.5-MoCa-7B-pretrain
```

Citation

If you find this model useful, please cite the following paper

@article{huang2024deciphering,
  title={Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate},
  author={Huang, Qidong and Dong, Xiaoyi and Zhang, Pan and Zang, Yuhang and Cao, Yuhang and Wang, Jiaqi and Lin, Dahua and Zhang, Weiming and Yu, Nenghai},
  journal={arXiv preprint arXiv:2410.07167},
  year={2024}
}

Downloads last month: 5

Safetensors

Model size

7B params

Tensor type

BF16

Inference Providers NEW

Image-Text-to-Text

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

Model tree for shikiw/LLaVA-v1.5-MoCa-7B-pretrain

Base model

lmsys/vicuna-7b-v1.5

Finetuned

(65)

this model

Dataset used to train shikiw/LLaVA-v1.5-MoCa-7B-pretrain

Paper for shikiw/LLaVA-v1.5-MoCa-7B-pretrain

Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate

Paper • 2410.07167 • Published Oct 9, 2024 • 39