zR commited on
Commit
98be0af
·
1 Parent(s): ec9fb99

change image

Browse files
Files changed (2) hide show
  1. README.md +6 -6
  2. README_zh.md +4 -4
README.md CHANGED
@@ -4,12 +4,12 @@ license_name: cogvlm2
4
  license_link: https://huggingface.co/THUDM/cogvlm2-video-llama3-base/blob/main/LICENSE
5
 
6
  language:
7
- - en
8
  pipeline_tag: text-generation
9
  tags:
10
- - chat
11
- - cogvlm2
12
- - cogvlm--video
13
 
14
  inference: false
15
  ---
@@ -99,9 +99,9 @@ our [github](https://github.com/THUDM/CogVLM2/tree/main/video_demo).
99
  ## License
100
 
101
  This model is released under the
102
- CogVLM2 [LICENSE](https://modelscope.cn/models/ZhipuAI/cogvlm2-video-llama3-base/file/view/master?fileName=LICENSE&status=0).
103
  For models built with Meta Llama 3, please also adhere to
104
- the [LLAMA3_LICENSE](https://modelscope.cn/models/ZhipuAI/cogvlm2-video-llama3-base/file/view/master?fileName=LLAMA3_LICENSE&status=0).
105
 
106
  ## Training details
107
 
 
4
  license_link: https://huggingface.co/THUDM/cogvlm2-video-llama3-base/blob/main/LICENSE
5
 
6
  language:
7
+ - en
8
  pipeline_tag: text-generation
9
  tags:
10
+ - chat
11
+ - cogvlm2
12
+ - cogvlm--video
13
 
14
  inference: false
15
  ---
 
99
  ## License
100
 
101
  This model is released under the
102
+ CogVLM2 [LICENSE](./LICENSE).
103
  For models built with Meta Llama 3, please also adhere to
104
+ the [LLAMA3_LICENSE](./LLAMA3_LICENSE).
105
 
106
  ## Training details
107
 
README_zh.md CHANGED
@@ -2,8 +2,8 @@
2
 
3
  ## 介绍
4
 
5
- CogVLM2-Video 在多个视频问答任务上实现了最先进的性能。能够实现一分钟内的视频理解。 我们提供了两个示例视频,分别展现了
6
- CogVLM2-Video 的 视频理解和时间序列定位能力。
7
  <table>
8
  <tr>
9
  <td>
@@ -77,9 +77,9 @@ prompt = f"The input consists of a sequence of key frames from a video. Answer t
77
  ## 模型协议
78
 
79
  此模型根据
80
- CogVLM2 [LICENSE](https://modelscope.cn/models/ZhipuAI/cogvlm2-video-llama3-base/file/view/master?fileName=LICENSE&status=0)
81
  发布。对于使用 Meta Llama 3 构建的模型,还请遵守
82
- [LLAMA3_LICENSE](https://modelscope.cn/models/ZhipuAI/cogvlm2-video-llama3-base/file/view/master?fileName=LLAMA3_LICENSE&status=0)。
83
 
84
  ## 引用
85
 
 
2
 
3
  ## 介绍
4
 
5
+ CogVLM2-Video 在多个视频问答任务上达到了 state-of-the-art 的性能,能够实现一分钟内的视频理解。
6
+ 我们提供了两个示例视频,分别展现了 CogVLM2-Video 的 视频理解和时间序列定位能力。
7
  <table>
8
  <tr>
9
  <td>
 
77
  ## 模型协议
78
 
79
  此模型根据
80
+ CogVLM2 [LICENSE](./LICENSE)
81
  发布。对于使用 Meta Llama 3 构建的模型,还请遵守
82
+ [LLAMA3_LICENSE](./LLAMA3_LICENSE)。
83
 
84
  ## 引用
85