Instructions to use MBZUAI/CoME-VL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MBZUAI/CoME-VL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="MBZUAI/CoME-VL")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MBZUAI/CoME-VL", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MBZUAI/CoME-VL with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MBZUAI/CoME-VL" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MBZUAI/CoME-VL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MBZUAI/CoME-VL
- SGLang
How to use MBZUAI/CoME-VL 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/CoME-VL" \ --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/CoME-VL", "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/CoME-VL" \ --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/CoME-VL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MBZUAI/CoME-VL with Docker Model Runner:
docker model run hf.co/MBZUAI/CoME-VL
Update README.md
Browse files
README.md
CHANGED
|
@@ -171,9 +171,9 @@ python3 scripts/convert_hf_to_molmo.py openai
|
|
| 171 |
If you find CoME-VL useful in your research, please consider citing:
|
| 172 |
```bibtex
|
| 173 |
@article{comevl2026,
|
| 174 |
-
title={CoME-VL: Scaling Complementary Multi-Encoder Vision-Language},
|
| 175 |
author={Deria, Ankan and Kumar, Komal and He, Xilin and Razzak, Imran and Cholakkal, Hisham and Khan, Fahad Shahbaz and Khan, Salman},
|
| 176 |
-
journal={arXiv preprint},
|
| 177 |
year={2026}
|
| 178 |
}
|
| 179 |
```
|
|
|
|
| 171 |
If you find CoME-VL useful in your research, please consider citing:
|
| 172 |
```bibtex
|
| 173 |
@article{comevl2026,
|
| 174 |
+
title={CoME-VL: Scaling Complementary Multi-Encoder Vision-Language Learning},
|
| 175 |
author={Deria, Ankan and Kumar, Komal and He, Xilin and Razzak, Imran and Cholakkal, Hisham and Khan, Fahad Shahbaz and Khan, Salman},
|
| 176 |
+
journal={arXiv preprint arXiv:2604.03231},
|
| 177 |
year={2026}
|
| 178 |
}
|
| 179 |
```
|