ynhe commited on
Commit
1037d18
·
verified ·
1 Parent(s): bff14a1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -0
README.md CHANGED
@@ -87,10 +87,21 @@ model-index:
87
 
88
 
89
  ## 📈 Performance
 
 
90
  | Model | MVBench | LongVideoBench | VideoMME(w/o sub)|
91
  | --- | --- | --- | --- |
92
  |InternVideo2.5| 75.7 | 60.6 | 65.1|
93
 
 
 
 
 
 
 
 
 
 
94
  ## 🚀 How to use the model
95
 
96
  First, you need to install [flash attention2](https://github.com/Dao-AILab/flash-attention) and some other modules. We provide a simple installation example below:
 
87
 
88
 
89
  ## 📈 Performance
90
+
91
+ - VideoBenchmark
92
  | Model | MVBench | LongVideoBench | VideoMME(w/o sub)|
93
  | --- | --- | --- | --- |
94
  |InternVideo2.5| 75.7 | 60.6 | 65.1|
95
 
96
+ - Inference Speed
97
+
98
+ We measured the average inference speed (tokens/s) of generating 1024 new tokens and 5198 (8192-2998) tokens with the context of an video (which takes 2998 tokens) under BF16 precision.
99
+
100
+ |Quantization | Speed (3022 tokens) | Speed (8192 tokens)|
101
+ |--- |--- |---|
102
+ |BF16 | 33.40 | 31.91 |
103
+
104
+
105
  ## 🚀 How to use the model
106
 
107
  First, you need to install [flash attention2](https://github.com/Dao-AILab/flash-attention) and some other modules. We provide a simple installation example below: