Improve Model Card: Correct pipeline tag, add library name and project page link

#1
by nielsr HF staff - opened
Files changed (1) hide show
  1. README.md +18 -6
README.md CHANGED
@@ -1,14 +1,16 @@
1
  ---
2
- license: apache-2.0
3
- datasets:
4
- - THUdyh/Oryx-SFT-Data
5
  base_model:
6
  - Qwen/Qwen2.5-7B-Instruct
7
- pipeline_tag: text-generation
 
8
  language:
9
  - en
10
  - zh
 
 
 
11
  ---
 
12
  # Oryx-1.5-7B
13
 
14
  ## Model Summary
@@ -18,6 +20,7 @@ The Oryx-1.5 models are 7/32B parameter models trained on [Oryx-SFT-Data](https:
18
  Oryx offers an on-demand solution to seamlessly and efficiently process visual inputs with arbitrary spatial sizes and temporal lengths.
19
 
20
  - **Repository:** https://github.com/Oryx-mllm/Oryx
 
21
  - **Languages:** English, Chinese
22
  - **Paper:** https://arxiv.org/abs/2409.12961
23
 
@@ -25,7 +28,7 @@ Oryx offers an on-demand solution to seamlessly and efficiently process visual i
25
 
26
  We provide a simple generation process for using our model. For more details, please refer to our [Github Repo](https://github.com/liuzuyan/oryx)
27
 
28
- ```
29
  from oryx.model.builder import load_pretrained_model
30
  from oryx.mm_utils import get_model_name_from_path, process_images, tokenizer_image_token
31
  from oryx.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN, IGNORE_INDEX
@@ -125,4 +128,13 @@ print(text_outputs)
125
  - **Orchestration:** HuggingFace Trainer
126
  - **Code:** Pytorch
127
 
128
- ## Citation
 
 
 
 
 
 
 
 
 
 
1
  ---
 
 
 
2
  base_model:
3
  - Qwen/Qwen2.5-7B-Instruct
4
+ datasets:
5
+ - THUdyh/Oryx-SFT-Data
6
  language:
7
  - en
8
  - zh
9
+ license: apache-2.0
10
+ pipeline_tag: video-text-to-text
11
+ library_name: oryx
12
  ---
13
+
14
  # Oryx-1.5-7B
15
 
16
  ## Model Summary
 
20
  Oryx offers an on-demand solution to seamlessly and efficiently process visual inputs with arbitrary spatial sizes and temporal lengths.
21
 
22
  - **Repository:** https://github.com/Oryx-mllm/Oryx
23
+ - **Project Page:** https://oryx-mllm.github.io
24
  - **Languages:** English, Chinese
25
  - **Paper:** https://arxiv.org/abs/2409.12961
26
 
 
28
 
29
  We provide a simple generation process for using our model. For more details, please refer to our [Github Repo](https://github.com/liuzuyan/oryx)
30
 
31
+ ```python
32
  from oryx.model.builder import load_pretrained_model
33
  from oryx.mm_utils import get_model_name_from_path, process_images, tokenizer_image_token
34
  from oryx.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN, IGNORE_INDEX
 
128
  - **Orchestration:** HuggingFace Trainer
129
  - **Code:** Pytorch
130
 
131
+ ## Citation
132
+
133
+ ```bibtex
134
+ @article{liu2024oryx,
135
+ title={Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution},
136
+ author={Liu, Zuyan and Dong, Yuhao and Liu, Ziwei and Hu, Winston and Lu, Jiwen and Rao, Yongming},
137
+ journal={arXiv preprint arXiv:2409.12961},
138
+ year={2024}
139
+ }
140
+ ```