Link model to paper and update metadata

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +13 -8
README.md CHANGED
@@ -1,14 +1,19 @@
1
  ---
 
 
2
  library_name: transformers
 
 
 
 
 
 
3
  tags:
4
  - vlm
5
  - image-text-to-text
6
  - multimodal
7
  - pretraining
8
- license: apache-2.0
9
- language:
10
- - en
11
- pipeline_tag: image-text-to-text
12
  ---
13
 
14
  # Dream-VL 7B
@@ -18,7 +23,7 @@ The model takes language instructions and images as input and generates language
18
 
19
  All Dream-VL checkpoints, as well as our [training codebase](https://github.com/DreamLM/Dream-VLX) are released under an Apache 2.0 License.
20
 
21
- For full details, please read [our blog](https://hkunlp.github.io/blog/2025/dream-vlx/) and paper (pending).
22
 
23
  ## Model Summary
24
 
@@ -27,7 +32,7 @@ For full details, please read [our blog](https://hkunlp.github.io/blog/2025/drea
27
  - **License:** apache-2.0
28
  - **Finetuned from:** [`Dream-7B`](https://huggingface.co/Dream-org/Dream-v0-Instruct-7B), with Qwen2ViT Vision Backbone.
29
  - **Pretraining Dataset:** [MAmmoTH-VL-Instruct-12M](https://huggingface.co/datasets/MAmmoTH-VL/MAmmoTH-VL-Instruct-12M).
30
- - **Repository:** [https://github.com/DreamLM/DreamVLX](https://github.com/DreamLM/Dream-VLX)
31
  - **Project Page & Videos:** [https://hkunlp.github.io/blog/2025/dream-vlx](https://hkunlp.github.io/blog/2025/dream-vlx/)
32
 
33
  ## Getting Started
@@ -133,8 +138,8 @@ for j in range(len(messages)):
133
  ```bibtex
134
  @article{ye2025dreamvla,
135
  title={Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone},
136
- author={Ye, Jiacheng and Gong, Shansan and Gao, Jiahui and Fan, Junming and Wu, Shuang and Bi, Wei and Bai, Haoli and Shang, Lifeng and Kong, Lingpeng},
137
- journal={arXiv preprint},
138
  year={2025}
139
  }
140
  ```
 
1
  ---
2
+ language:
3
+ - en
4
  library_name: transformers
5
+ license: apache-2.0
6
+ pipeline_tag: image-text-to-text
7
+ base_model: Dream-org/Dream-v0-Instruct-7B
8
+ datasets:
9
+ - MAmmoTH-VL/MAmmoTH-VL-Instruct-12M
10
+ arxiv: 2512.22615
11
  tags:
12
  - vlm
13
  - image-text-to-text
14
  - multimodal
15
  - pretraining
16
+ - diffusion
 
 
 
17
  ---
18
 
19
  # Dream-VL 7B
 
23
 
24
  All Dream-VL checkpoints, as well as our [training codebase](https://github.com/DreamLM/Dream-VLX) are released under an Apache 2.0 License.
25
 
26
+ For full details, please read [our blog](https://hkunlp.github.io/blog/2025/dream-vlx/) and the paper: [Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone](https://huggingface.co/papers/2512.22615).
27
 
28
  ## Model Summary
29
 
 
32
  - **License:** apache-2.0
33
  - **Finetuned from:** [`Dream-7B`](https://huggingface.co/Dream-org/Dream-v0-Instruct-7B), with Qwen2ViT Vision Backbone.
34
  - **Pretraining Dataset:** [MAmmoTH-VL-Instruct-12M](https://huggingface.co/datasets/MAmmoTH-VL/MAmmoTH-VL-Instruct-12M).
35
+ - **Repository:** [https://github.com/DreamLM/Dream-VLX](https://github.com/DreamLM/Dream-VLX)
36
  - **Project Page & Videos:** [https://hkunlp.github.io/blog/2025/dream-vlx](https://hkunlp.github.io/blog/2025/dream-vlx/)
37
 
38
  ## Getting Started
 
138
  ```bibtex
139
  @article{ye2025dreamvla,
140
  title={Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone},
141
+ author={Ye, Jiacheng and Gong, Shansan and Gao, Jiahui and Fan, Junming and Wu, Shuang} and Bi, Wei and Bai, Haoli and Shang, Lifeng and Kong, Lingpeng},
142
+ journal={arXiv preprint arXiv:2512.22615},
143
  year={2025}
144
  }
145
  ```