Upload folder using huggingface_hub

README.md

@@ -75,8 +75,8 @@ InternVL 2.0 is a multimodal large language model series, featuring models of va
 | MVBench | - | - | - | 72.5 | 69.6 |
 | MMBench-Video<sub>8f</sub> | 1.62 | 1.53 | 1.30 | 1.32 | 1.37 |
 | MMBench-Video<sub>16f</sub> | 1.86 | 1.68 | 1.60 | 1.45 | 1.52 |
-| Video-MME<br>w/o subs | 71.9 | 59.9 | 75.0 | 61.2 | TODO |
-| Video-MME<br>w subs | 77.2 | 63.3 | 81.3 | 62.4 | TODO |
+| Video-MME<br>w/o subs | 71.9 | 59.9 | 75.0 | 61.2 | 61.2 |
+| Video-MME<br>w subs | 77.2 | 63.3 | 81.3 | 62.4 | 62.8 |
 
 - We evaluate our models on MVBench and Video-MME by extracting 16 frames from each video, and each frame was resized to a 448x448 image.
 
@@ -495,8 +495,8 @@ InternVL 2.0 是一个多模态大语言模型系列，包含各种规模的模
 | MVBench | - | - | - | 72.5 | 69.6 |
 | MMBench-Video<sub>8f</sub> | 1.62 | 1.53 | 1.30 | 1.32 | 1.37 |
 | MMBench-Video<sub>16f</sub> | 1.86 | 1.68 | 1.60 | 1.45 | 1.52 |
-| Video-MME<br>w/o subs | 71.9 | 59.9 | 75.0 | 61.2 | TODO |
-| Video-MME<br>w subs | 77.2 | 63.3 | 81.3 | 62.4 | TODO |
+| Video-MME<br>w/o subs | 71.9 | 59.9 | 75.0 | 61.2 | 61.2 |
+| Video-MME<br>w subs | 77.2 | 63.3 | 81.3 | 62.4 | 62.8 |
 
 - 我们通过从每个视频中提取 16 帧来评估我们的模型在 MVBench 和 Video-MME 上的性能，每个视频帧被调整为 448x448 的图像。