Instructions to use omkarthawakar/EvoLMM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use omkarthawakar/EvoLMM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="omkarthawakar/EvoLMM")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("omkarthawakar/EvoLMM", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use omkarthawakar/EvoLMM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "omkarthawakar/EvoLMM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "omkarthawakar/EvoLMM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/omkarthawakar/EvoLMM
- SGLang
How to use omkarthawakar/EvoLMM 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 "omkarthawakar/EvoLMM" \ --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": "omkarthawakar/EvoLMM", "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 "omkarthawakar/EvoLMM" \ --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": "omkarthawakar/EvoLMM", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use omkarthawakar/EvoLMM with Docker Model Runner:
docker model run hf.co/omkarthawakar/EvoLMM
Update README.md
Browse files
README.md
CHANGED
|
@@ -107,11 +107,14 @@ Weights and code follow the licenses of the base model and this repository. Chec
|
|
| 107 |
If you use these adapters, please cite EvoLMM:
|
| 108 |
|
| 109 |
```bibtex
|
| 110 |
-
@
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
|
|
|
|
|
|
|
|
|
| 115 |
}
|
| 116 |
```
|
| 117 |
|
|
|
|
| 107 |
If you use these adapters, please cite EvoLMM:
|
| 108 |
|
| 109 |
```bibtex
|
| 110 |
+
@misc{thawakar2025evolmmselfevolvinglargemultimodal,
|
| 111 |
+
title={EvoLMM: Self-Evolving Large Multimodal Models with Continuous Rewards},
|
| 112 |
+
author={Omkar Thawakar and Shravan Venkatraman and Ritesh Thawkar and Abdelrahman Shaker and Hisham Cholakkal and Rao Muhammad Anwer and Salman Khan and Fahad Khan},
|
| 113 |
+
year={2025},
|
| 114 |
+
eprint={2511.16672},
|
| 115 |
+
archivePrefix={arXiv},
|
| 116 |
+
primaryClass={cs.CV},
|
| 117 |
+
url={https://arxiv.org/abs/2511.16672},
|
| 118 |
}
|
| 119 |
```
|
| 120 |
|