Add pipeline tag, link to paper
#2
by
nielsr
HF staff
- opened
README.md
CHANGED
|
@@ -4,6 +4,7 @@ datasets:
|
|
| 4 |
- shenxq/VideoChat2
|
| 5 |
base_model:
|
| 6 |
- Vision-CAIR/LongVU_Qwen2_7B_img
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: llava-onevision-qwen-7b-ov
|
| 9 |
results:
|
|
@@ -50,6 +51,8 @@ model-index:
|
|
| 50 |
---
|
| 51 |
# LongVU
|
| 52 |
|
|
|
|
|
|
|
| 53 |
Play with the model on the [HF demo](https://huggingface.co/spaces/Vision-CAIR/LongVU).
|
| 54 |
|
| 55 |
<div align="left">
|
|
|
|
| 4 |
- shenxq/VideoChat2
|
| 5 |
base_model:
|
| 6 |
- Vision-CAIR/LongVU_Qwen2_7B_img
|
| 7 |
+
pipeline_tag: video-text-to-text
|
| 8 |
model-index:
|
| 9 |
- name: llava-onevision-qwen-7b-ov
|
| 10 |
results:
|
|
|
|
| 51 |
---
|
| 52 |
# LongVU
|
| 53 |
|
| 54 |
+
This repository contains the model based on Qwen2-7B as presented in [LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding](https://huggingface.co/papers/2410.17434).
|
| 55 |
+
|
| 56 |
Play with the model on the [HF demo](https://huggingface.co/spaces/Vision-CAIR/LongVU).
|
| 57 |
|
| 58 |
<div align="left">
|