Instructions to use MBZUAI/GLaMM-FullScope with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MBZUAI/GLaMM-FullScope with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MBZUAI/GLaMM-FullScope")# Load model directly from transformers import AutoProcessor, AutoModelForCausalLM processor = AutoProcessor.from_pretrained("MBZUAI/GLaMM-FullScope") model = AutoModelForCausalLM.from_pretrained("MBZUAI/GLaMM-FullScope") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use MBZUAI/GLaMM-FullScope with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MBZUAI/GLaMM-FullScope" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MBZUAI/GLaMM-FullScope", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MBZUAI/GLaMM-FullScope
- SGLang
How to use MBZUAI/GLaMM-FullScope 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 "MBZUAI/GLaMM-FullScope" \ --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": "MBZUAI/GLaMM-FullScope", "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 "MBZUAI/GLaMM-FullScope" \ --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": "MBZUAI/GLaMM-FullScope", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MBZUAI/GLaMM-FullScope with Docker Model Runner:
docker model run hf.co/MBZUAI/GLaMM-FullScope
metadata
license: apache-2.0
ποΈ GLaMM-FullScope
π Description
GLaMM-FullScope encompasses all capabilities of GLaMM, which is mixed finetuned with many open-source datasets. "Full" signifies its comprehensive nature, incorporating the full range of GLaMM capabilities including Grounded Conversation Generation (GCG), Referring Expression Segmentation, Region-level Captioning, Image-level captioning and Visual Question Answering.
π» Download
To get started with GLaMM-FullScope, follow these steps:
git lfs install
git clone https://huggingface.co/MBZUAI/GLaMM-FullScope
π Additional Resources
- Paper: ArXiv.
- GitHub Repository: For training and updates: GitHub - GLaMM.
- Project Page: For a detailed overview and insights into the project, visit our Project Page - GLaMM.
π Citations and Acknowledgments
@article{hanoona2023GLaMM,
title={GLaMM: Pixel Grounding Large Multimodal Model},
author={Rasheed, Hanoona and Maaz, Muhammad and Shaji, Sahal and Shaker, Abdelrahman and Khan, Salman and Cholakkal, Hisham and Anwer, Rao M. and Xing, Eric and Yang, Ming-Hsuan and Khan, Fahad S.},
journal={ArXiv 2311.03356},
year={2023}
}