Image-Text-to-Text
Transformers
English
finance
medical
AD
MLLM-CL
Sci
RS
Math
OCR
Count
GUI-Agent
DCL
ACL
llava
multimodal
image-to-text
text-generation
Instructions to use MLLM-CL/MRLoRA_Experts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MLLM-CL/MRLoRA_Experts with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="MLLM-CL/MRLoRA_Experts")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MLLM-CL/MRLoRA_Experts", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use MLLM-CL/MRLoRA_Experts with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MLLM-CL/MRLoRA_Experts" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MLLM-CL/MRLoRA_Experts", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MLLM-CL/MRLoRA_Experts
- SGLang
How to use MLLM-CL/MRLoRA_Experts 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 "MLLM-CL/MRLoRA_Experts" \ --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": "MLLM-CL/MRLoRA_Experts", "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 "MLLM-CL/MRLoRA_Experts" \ --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": "MLLM-CL/MRLoRA_Experts", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MLLM-CL/MRLoRA_Experts with Docker Model Runner:
docker model run hf.co/MLLM-CL/MRLoRA_Experts
Update README.md
Browse files
README.md
CHANGED
|
@@ -20,4 +20,33 @@ tags:
|
|
| 20 |
- GUI-Agent
|
| 21 |
- DCL
|
| 22 |
- ACL
|
| 23 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
- GUI-Agent
|
| 21 |
- DCL
|
| 22 |
- ACL
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
## MLLM-CL Benchmark Description
|
| 26 |
+
MLLM-CL is a novel benchmark encompassing domain and ability continual learning, where the former focuses on independently and identically distributed (IID) evaluation across evolving mainstream domains,
|
| 27 |
+
whereas the latter evaluates on non-IID scenarios with emerging model ability.
|
| 28 |
+
For more details, please refer to:
|
| 29 |
+
|
| 30 |
+
**MLLM-CL: Continual Learning for Multimodal Large Language Models** [[paper](https://arxiv.org/abs/2506.05453)], [[code](https://github.com/bjzhb666/MLLM-CL/)].
|
| 31 |
+
|
| 32 |
+
[Hongbo Zhao](https://scholar.google.com/citations?user=Gs22F0UAAAAJ&hl=zh-CN), [Fei Zhu](https://impression2805.github.io/), [Haiyang Guo](https://ghy0501.github.io/guohaiyang0501.github.io/), [Meng Wang](https://moenupa.github.io/), Rundong Wang, [Gaofeng Meng](https://scholar.google.com/citations?hl=zh-CN&user=5hti_r0AAAAJ), [Zhaoxiang Zhang](https://scholar.google.com/citations?hl=zh-CN&user=qxWfV6cAAAAJ)
|
| 33 |
+
|
| 34 |
+
## Usage
|
| 35 |
+
This repo is used to open-source all the experts in MLLM-CL experiments, including 4 branches.
|
| 36 |
+
|
| 37 |
+
## Citation
|
| 38 |
+
```
|
| 39 |
+
@article{zhao2025mllm,
|
| 40 |
+
title={MLLM-CL: Continual Learning for Multimodal Large Language Models},
|
| 41 |
+
author={Zhao, Hongbo and Zhu, Fei and Guo, Haiyang and Wang, Meng and Wang, Rundong and Meng, Gaofeng and Zhang, Zhaoxiang},
|
| 42 |
+
journal={arXiv preprint arXiv:2506.05453},
|
| 43 |
+
year={2025}
|
| 44 |
+
}
|
| 45 |
+
```
|
| 46 |
+
## Contact
|
| 47 |
+
Please post an issue in our Github.
|
| 48 |
+
|
| 49 |
+
## About us: MLLM-CL Community
|
| 50 |
+

|
| 51 |
+
We are the members from MLLM-CL, an open-source community focus on Continual learning of Multimodal Large Language Models.
|
| 52 |
+
If you are interested in our community, feel free to contact us in github or email.
|