Add pipeline tag, links to paper, project page, and repository
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,7 +1,8 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
library_name: transformers
|
| 4 |
base_model: Qwen/Qwen3-VL-4B-Instruct
|
|
|
|
|
|
|
|
|
|
| 5 |
tags:
|
| 6 |
- video-retrieval
|
| 7 |
- temporal-grounding
|
|
@@ -10,11 +11,16 @@ tags:
|
|
| 10 |
|
| 11 |
# VideoSearch-R1 Charades-STA Stage 2
|
| 12 |
|
| 13 |
-
This is the Stage 2 VideoSearch-R1 checkpoint trained for Charades-STA.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
Use with the VideoSearch-R1 codebase:
|
| 16 |
|
| 17 |
```bash
|
| 18 |
bash scripts/data_construct/download_preextracted_data.bash charades
|
| 19 |
EVAL_GPUS=0 bash scripts/inference/inference.bash charades --checkpoint VideoSearchR1/charades-stage2
|
| 20 |
-
```
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
base_model: Qwen/Qwen3-VL-4B-Instruct
|
| 3 |
+
library_name: transformers
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
pipeline_tag: video-text-to-text
|
| 6 |
tags:
|
| 7 |
- video-retrieval
|
| 8 |
- temporal-grounding
|
|
|
|
| 11 |
|
| 12 |
# VideoSearch-R1 Charades-STA Stage 2
|
| 13 |
|
| 14 |
+
This is the Stage 2 VideoSearch-R1 checkpoint trained for Charades-STA, presented in the paper [VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement](https://huggingface.co/papers/2607.00446).
|
| 15 |
+
|
| 16 |
+
- **Project Page:** [https://mlvlab.github.io/VideoSearch-R1/](https://mlvlab.github.io/VideoSearch-R1/)
|
| 17 |
+
- **Repository:** [https://github.com/mlvlab/VideoSearch-R1](https://github.com/mlvlab/VideoSearch-R1)
|
| 18 |
+
|
| 19 |
+
## Usage
|
| 20 |
|
| 21 |
Use with the VideoSearch-R1 codebase:
|
| 22 |
|
| 23 |
```bash
|
| 24 |
bash scripts/data_construct/download_preextracted_data.bash charades
|
| 25 |
EVAL_GPUS=0 bash scripts/inference/inference.bash charades --checkpoint VideoSearchR1/charades-stage2
|
| 26 |
+
```
|