Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,16 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# InternVideo2-B14
|
| 6 |
+
### Cross-Modal and Vision-Language Model Checkpoints
|
| 7 |
+
|
| 8 |
+
This repository hosts pre-trained model checkpoints for cross-modal video-text understanding, vision-language alignment, and efficient deployment. Below is a summary of included files:
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
| Filename | Size | Description |
|
| 12 |
+
|-------------------------|---------|-----------------------------------------------------------------------------|
|
| 13 |
+
| cross_mamba_film_ckpt.pt | 504 MB | A cross-modal checkpoint combining vision and text using **FiLM** (Feature-wise Linear Modulation) layers, optimized for Mamba architecture. |
|
| 14 |
+
| internvideo2_clip.pt | 5.55 MB | CLIP component of **InternVideo2-B14** |
|
| 15 |
+
| internvideo2_vision.pt | 205 MB | Vision encoder backbone for **InternVideo2-B14** |
|
| 16 |
+
| mobileclip_blt.pt | 599 MB | Lightweight **MobileCLIP** variant (BLT) |
|