Upload folder using huggingface_hub
Browse files
    	
        README.md
    CHANGED
    
    | @@ -55,13 +55,13 @@ InternVL 2.0 is a multimodal large language model series, featuring models of va | |
| 55 |  | 
| 56 | 
             
            ### Video Benchmarks
         | 
| 57 |  | 
| 58 | 
            -
            | | 
| 59 | 
            -
            |  | 
| 60 | 
            -
            | | 
| 61 | 
            -
            | | 
| 62 | 
            -
            | | 
| 63 | 
            -
            | Video-MME< | 
| 64 | 
            -
            | Video-MME< | 
| 65 |  | 
| 66 | 
             
            - We evaluate our models on MVBench by extracting 16 frames from each video, and each frame was resized to a 448x448 image.
         | 
| 67 |  | 
| @@ -468,13 +468,13 @@ InternVL 2.0 是一个多模态大语言模型系列,包含各种规模的模 | |
| 468 |  | 
| 469 | 
             
            ### 视频相关评测
         | 
| 470 |  | 
| 471 | 
            -
            | | 
| 472 | 
            -
            |  | 
| 473 | 
            -
            | | 
| 474 | 
            -
            | | 
| 475 | 
            -
            | | 
| 476 | 
            -
            | Video-MME< | 
| 477 | 
            -
            | Video-MME< | 
| 478 |  | 
| 479 | 
             
            - 我们通过从每个视频中提取16帧来评估我们的模型在MVBench上的性能,每个视频帧被调整为448x448的图像。
         | 
| 480 |  | 
|  | |
| 55 |  | 
| 56 | 
             
            ### Video Benchmarks
         | 
| 57 |  | 
| 58 | 
            +
            |      Benchmark       | VideoChat2-Phi3 | VideoChat2-HD-Mistral | Mini-InternVL-2B-1-5 | InternVL2-2B |
         | 
| 59 | 
            +
            | :------------------: | :-------------: | :-------------------: | :------------------: | :----------: |
         | 
| 60 | 
            +
            |      Model Size      |       4B        |          7B           |         2.2B         |     2.2B     |
         | 
| 61 | 
            +
            |                      |                 |                       |                      |              |
         | 
| 62 | 
            +
            |       MVBench        |      55.1       |         60.4          |         37.0         |     60.2     |
         | 
| 63 | 
            +
            | Video-MME<br>wo subs |        -        |         42.3          |         TBD          |     TBD      |
         | 
| 64 | 
            +
            | Video-MME<br>w/ subs |        -        |         54.6          |         TBD          |     TBD      |
         | 
| 65 |  | 
| 66 | 
             
            - We evaluate our models on MVBench by extracting 16 frames from each video, and each frame was resized to a 448x448 image.
         | 
| 67 |  | 
|  | |
| 468 |  | 
| 469 | 
             
            ### 视频相关评测
         | 
| 470 |  | 
| 471 | 
            +
            |      评测数据集      | VideoChat2-Phi3 | VideoChat2-HD-Mistral | Mini-InternVL-2B-1-5 | InternVL2-2B |
         | 
| 472 | 
            +
            | :------------------: | :-------------: | :-------------------: | :------------------: | :----------: |
         | 
| 473 | 
            +
            |       模型大小       |       4B        |          7B           |         2.2B         |     2.2B     |
         | 
| 474 | 
            +
            |                      |                 |                       |                      |              |
         | 
| 475 | 
            +
            |       MVBench        |      55.1       |         60.4          |         37.0         |     60.2     |
         | 
| 476 | 
            +
            | Video-MME<br>wo subs |        -        |         42.3          |         TBD          |     TBD      |
         | 
| 477 | 
            +
            | Video-MME<br>w/ subs |        -        |         54.6          |         TBD          |     TBD      |
         | 
| 478 |  | 
| 479 | 
             
            - 我们通过从每个视频中提取16帧来评估我们的模型在MVBench上的性能,每个视频帧被调整为448x448的图像。
         | 
| 480 |  | 
