Feature Extraction
Transformers
Safetensors
English
penguinvl_vision_encoder
multi-modal
large-language-model
vision-language-model
vision-encoder
custom_code
Instructions to use tencent/Penguin-Encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tencent/Penguin-Encoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="tencent/Penguin-Encoder", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("tencent/Penguin-Encoder", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
#1
by rhyang - opened
README.md
CHANGED
|
@@ -103,5 +103,10 @@ Main Results can see the ablation section in our paper.
|
|
| 103 |
|
| 104 |
If you find Penguin-VL useful for your research and applications, please cite using this BibTeX:
|
| 105 |
```bibtex
|
| 106 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 107 |
```
|
|
|
|
| 103 |
|
| 104 |
If you find Penguin-VL useful for your research and applications, please cite using this BibTeX:
|
| 105 |
```bibtex
|
| 106 |
+
@article{Penguin-VL,
|
| 107 |
+
title={Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders},
|
| 108 |
+
author={Boqiang Zhang and Lei Ke and Ruihan Yang and Qi Gao and Tianyuan Qu and Rossell Chen and Dong Yu and Leoweiliang},
|
| 109 |
+
journal={arXiv preprint arXiv:2603.06569},
|
| 110 |
+
year={2026}
|
| 111 |
+
}
|
| 112 |
```
|