Image-Text-to-Text
Transformers
Safetensors
English
Chinese
qwen3_5
feature-extraction
wemm
multimodal
video
audio
conversational
custom_code
Instructions to use tencent/WeMM-Video-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tencent/WeMM-Video-4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="tencent/WeMM-Video-4B", trust_remote_code=True) messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("tencent/WeMM-Video-4B", trust_remote_code=True) model = AutoModel.from_pretrained("tencent/WeMM-Video-4B", trust_remote_code=True, device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use tencent/WeMM-Video-4B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tencent/WeMM-Video-4B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tencent/WeMM-Video-4B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/tencent/WeMM-Video-4B
- SGLang
How to use tencent/WeMM-Video-4B 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 "tencent/WeMM-Video-4B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tencent/WeMM-Video-4B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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 "tencent/WeMM-Video-4B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tencent/WeMM-Video-4B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use tencent/WeMM-Video-4B with Docker Model Runner:
docker model run hf.co/tencent/WeMM-Video-4B
Update model card with evaluation and paper links
Browse files- README.md +13 -6
- SHA256SUMS +1 -1
README.md
CHANGED
|
@@ -14,7 +14,7 @@ tags:
|
|
| 14 |
|
| 15 |
# WeMM-Video-4B
|
| 16 |
|
| 17 |
-
[Project](https://github.com/Tencent/WeMM-Video) 路 [Model Collection](https://huggingface.co/collections/tencent/wemm-video)
|
| 18 |
|
| 19 |
## Overview
|
| 20 |
|
|
@@ -156,6 +156,10 @@ Set `fps` and `max_frames` inside `video_url` to control sampling for a clip. Se
|
|
| 156 |
|
| 157 |
Patched vLLM loaded the checkpoint on H20 and completed generation checks for text, image, audio, and video with a soundtrack. The local checkpoint also passed direct Transformers loading and a CPU text generation check.
|
| 158 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 159 |
## License
|
| 160 |
|
| 161 |
Apache License 2.0. See the [included license](LICENSE) and the [collection license and third-party attribution](https://github.com/Tencent/WeMM-Video/blob/main/LICENSE). Third-party components remain subject to their original terms.
|
|
@@ -163,10 +167,13 @@ Apache License 2.0. See the [included license](LICENSE) and the [collection lice
|
|
| 163 |
## Citation
|
| 164 |
|
| 165 |
```bibtex
|
| 166 |
-
@misc{
|
| 167 |
-
|
| 168 |
-
|
| 169 |
-
|
| 170 |
-
|
|
|
|
|
|
|
|
|
|
| 171 |
}
|
| 172 |
```
|
|
|
|
| 14 |
|
| 15 |
# WeMM-Video-4B
|
| 16 |
|
| 17 |
+
[Project](https://github.com/Tencent/WeMM-Video) 路 [Model Collection](https://huggingface.co/collections/tencent/wemm-video) 路 [](https://arxiv.org/abs/2611.26409) 路 [Hugging Face Paper](https://huggingface.co/papers/2611.26409)
|
| 18 |
|
| 19 |
## Overview
|
| 20 |
|
|
|
|
| 156 |
|
| 157 |
Patched vLLM loaded the checkpoint on H20 and completed generation checks for text, image, audio, and video with a soundtrack. The local checkpoint also passed direct Transformers loading and a CPU text generation check.
|
| 158 |
|
| 159 |
+
## Evaluation
|
| 160 |
+
|
| 161 |
+
See the [WeMM-Video-35B-A3B evaluation results](https://huggingface.co/tencent/WeMM-Video-35BA3B#evaluation) for the benchmark comparison in the technical report.
|
| 162 |
+
|
| 163 |
## License
|
| 164 |
|
| 165 |
Apache License 2.0. See the [included license](LICENSE) and the [collection license and third-party attribution](https://github.com/Tencent/WeMM-Video/blob/main/LICENSE). Third-party components remain subject to their original terms.
|
|
|
|
| 167 |
## Citation
|
| 168 |
|
| 169 |
```bibtex
|
| 170 |
+
@misc{WeMM-Video,
|
| 171 |
+
title={WeMM-Video: Pushing the Frontiers of Open-Source Omni-Modal Video Understanding},
|
| 172 |
+
author={Changli Tang and Jie Yang and Tianyi Wang and Lei Li and Daoze Zhang and Zijie Xin and Zhan Liu and Li Li and Jinchang Xu and Fengyun Rao and Chao Zhang and Jing Lyu},
|
| 173 |
+
year={2026},
|
| 174 |
+
eprint={2611.26409},
|
| 175 |
+
archivePrefix={arXiv},
|
| 176 |
+
primaryClass={cs.CV},
|
| 177 |
+
url={https://arxiv.org/abs/2611.26409},
|
| 178 |
}
|
| 179 |
```
|
SHA256SUMS
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
bac4d42ddebadb11e405fc4de2335579e67676362ac870108012ab4899ef1e5b LICENSE
|
| 2 |
-
|
| 3 |
5cf26c5a561880138295ce9921c270e1a4c5ca7ac11b489b83fb9c8acbebaf37 README_PROCESSOR.md
|
| 4 |
273d8e0e683b885071fb17e08d71e5f2a5ddfb5309756181681de4f5a1822d80 chat_template.jinja
|
| 5 |
5eca5c5955cdc4ec20ddb433053130c690304a0a26c2dcd031daef032b7235a4 config.json
|
|
|
|
| 1 |
bac4d42ddebadb11e405fc4de2335579e67676362ac870108012ab4899ef1e5b LICENSE
|
| 2 |
+
8e3e1d168b76c0a2161bd988cecd2da9fae4f59b8577eedf1054a100698f05f1 README.md
|
| 3 |
5cf26c5a561880138295ce9921c270e1a4c5ca7ac11b489b83fb9c8acbebaf37 README_PROCESSOR.md
|
| 4 |
273d8e0e683b885071fb17e08d71e5f2a5ddfb5309756181681de4f5a1822d80 chat_template.jinja
|
| 5 |
5eca5c5955cdc4ec20ddb433053130c690304a0a26c2dcd031daef032b7235a4 config.json
|