XCLiu commited on
Commit
df0b5a6
1 Parent(s): 311f96c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -3
README.md CHANGED
@@ -37,6 +37,11 @@ On the basis of `Python >= 3.8` environment, install the necessary dependencies
37
  pip install -e .
38
  ```
39
 
 
 
 
 
 
40
  ### Simple Inference Example
41
 
42
  ```python
@@ -121,10 +126,14 @@ This code repository is licensed under [MIT License](./LICENSE-CODE). The use of
121
  ## 5. Citation
122
 
123
  ```
124
- @misc{wu2024deepseekvl2,
125
- title={DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding},
126
- author={Wu, Zhiyu and Chen, Xiaokang and Pan, Zizheng and Liu, Xingchao and Liu, Wen and Dai, Damai and Gao, Huazuo and Ma, Yiyang and Wu, Chengyue and Wang, Bingxuan and Xie, Zhenda and Wu, Yu and Hu, Kai and Wang, Jiawei and Sun, Yaofeng and Li, Yukun and Piao, Yishi and Guan, Kang and Liu, Aixin and Xie, Xin and You, Yuxiang and Dong, Kai and Yu, Xingkai and Zhang, Haowei and Zhao, Liang and Wang, Yisong and Ruan, Chong},
127
  year={2024},
 
 
 
 
128
  }
129
  ```
130
 
 
37
  pip install -e .
38
  ```
39
 
40
+ ### Notifications
41
+ 1. We suggest to use a temperature T <= 0.7 when sampling. We observe a larger temperature decreases the generation quality.
42
+ 2. To keep the number of tokens managable in the context window, we apply dynamic tiling strategy to <=2 images. When there are >=3 images, we directly pad the images to 384*384 as inputs without tiling.
43
+ 3. The main difference between DeepSeek-VL2-Tiny, DeepSeek-VL2-Small and DeepSeek-VL2 is the base LLM.
44
+
45
  ### Simple Inference Example
46
 
47
  ```python
 
126
  ## 5. Citation
127
 
128
  ```
129
+ @misc{wu2024deepseekvl2mixtureofexpertsvisionlanguagemodels,
130
+ title={DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding},
131
+ author={Zhiyu Wu and Xiaokang Chen and Zizheng Pan and Xingchao Liu and Wen Liu and Damai Dai and Huazuo Gao and Yiyang Ma and Chengyue Wu and Bingxuan Wang and Zhenda Xie and Yu Wu and Kai Hu and Jiawei Wang and Yaofeng Sun and Yukun Li and Yishi Piao and Kang Guan and Aixin Liu and Xin Xie and Yuxiang You and Kai Dong and Xingkai Yu and Haowei Zhang and Liang Zhao and Yisong Wang and Chong Ruan},
132
  year={2024},
133
+ eprint={2412.10302},
134
+ archivePrefix={arXiv},
135
+ primaryClass={cs.CV},
136
+ url={https://arxiv.org/abs/2412.10302},
137
  }
138
  ```
139