Instructions to use weizhiwang/mlm-filter-llava-13b-gpt4v with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use weizhiwang/mlm-filter-llava-13b-gpt4v with Transformers:

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

pipe = pipeline("text-generation", model="weizhiwang/mlm-filter-llava-13b-gpt4v")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("weizhiwang/mlm-filter-llava-13b-gpt4v")
model = AutoModelForCausalLM.from_pretrained("weizhiwang/mlm-filter-llava-13b-gpt4v", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use weizhiwang/mlm-filter-llava-13b-gpt4v with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "weizhiwang/mlm-filter-llava-13b-gpt4v"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "weizhiwang/mlm-filter-llava-13b-gpt4v",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/weizhiwang/mlm-filter-llava-13b-gpt4v

SGLang

How to use weizhiwang/mlm-filter-llava-13b-gpt4v 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 "weizhiwang/mlm-filter-llava-13b-gpt4v" \
    --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": "weizhiwang/mlm-filter-llava-13b-gpt4v",
		"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 "weizhiwang/mlm-filter-llava-13b-gpt4v" \
        --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": "weizhiwang/mlm-filter-llava-13b-gpt4v",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use weizhiwang/mlm-filter-llava-13b-gpt4v with Docker Model Runner:
```
docker model run hf.co/weizhiwang/mlm-filter-llava-13b-gpt4v
```

MLM-Filter-13b Model Card

Model details

Model type: MLM-Filter-13b is an open-source MLLM trained to assess the data quality of image-text paired data. It can generate 4 quality metrics for image-text data: Image Text Matching, Object Detail Fulfillment, Caption Text Quality, and Semantic Understanding.

Model date: MLM-Filter-13B was trained in Dec 2023.

Paper or resources for more information: https://mlm-filter.github.io/

@article{wang2024finetuned,
  title={Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters},
  author={Wang, Weizhi and Mrini, Khalil and Yang, Linjie and Kumar, Sateesh and Tian, Yu and Yan, Xifeng and Wang, Heng},
  journal={arXiv preprint arXiv:2403.02677},
  year={2024}
}

License

Where to send questions or comments about the model: https://github.com/Victorwz/MLM_Filter/issues

Intended use

Primary intended uses: MLM-Filter can be used as a drop-in replacement for CLIPScore in these tasks:

Score image-text data in large-scale pre-training dataset and then filter high-quality subsets based on the scores (For training MLLMs or VLMs, please consider to jointly use the Image-Text Matching score and the Object Detail Fulfillment score);
Evaluate the image-text alignment for image2text or text2image generation models;
Any potential applications with the need to calculate the image-text alignment.

Training dataset

46k instruction sampled from LLaVA-1.5 665k data.
4k instructions on image-text data quality assessment tasks ranging across 4 metrics.

Usage Sample

Please follow the instructions in https://github.com/Victorwz/MLM_Filter.

Downloads last month: 22

Collection including weizhiwang/mlm-filter-llava-13b-gpt4v

MLM-Filter Model and Data

Collection

The collections of proposed MLM-Filter models based on different LLM backbones. • 3 items • Updated Mar 2 • 1

Paper for weizhiwang/mlm-filter-llava-13b-gpt4v

Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters

Paper • 2403.02677 • Published Mar 5, 2024 • 18