Updates README.md
Browse files
README.md
CHANGED
@@ -8,7 +8,7 @@ license: apache-2.0
|
|
8 |
## π Description
|
9 |
VideoGPT+ integrates image and video encoders to leverage detailed spatial understanding and global temporal context, respectively. It processes videos in segments using adaptive pooling on features from both encoders, enhancing performance across various video benchmarks.
|
10 |
|
11 |
-
This model contains VideoGPT+ checkpoints with Phi-3-Mini-4K 3.8B LLM for VCGBench, VCGBench-Diverse and MVBench benchmarks
|
12 |
|
13 |
## π» Download
|
14 |
To get started with GLaMM-FullScope, follow these steps:
|
|
|
8 |
## π Description
|
9 |
VideoGPT+ integrates image and video encoders to leverage detailed spatial understanding and global temporal context, respectively. It processes videos in segments using adaptive pooling on features from both encoders, enhancing performance across various video benchmarks.
|
10 |
|
11 |
+
**This model contains VideoGPT+ checkpoints with Phi-3-Mini-4K 3.8B LLM for VCGBench, VCGBench-Diverse and MVBench benchmarks.**
|
12 |
|
13 |
## π» Download
|
14 |
To get started with GLaMM-FullScope, follow these steps:
|