Instructions to use TIGER-Lab/VideoScore-Qwen2-VL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TIGER-Lab/VideoScore-Qwen2-VL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="TIGER-Lab/VideoScore-Qwen2-VL")# Load model directly from transformers import AutoProcessor, AutoModelForSequenceClassification processor = AutoProcessor.from_pretrained("TIGER-Lab/VideoScore-Qwen2-VL") model = AutoModelForSequenceClassification.from_pretrained("TIGER-Lab/VideoScore-Qwen2-VL", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -95,11 +95,6 @@ model = Qwen2VLForSequenceClassification.from_pretrained(
|
|
| 95 |
# default processer
|
| 96 |
processor = Qwen2VLProcessor.from_pretrained(model_name)
|
| 97 |
|
| 98 |
-
|
| 99 |
-
model.push_to_hub("TIGER-Lab/VideoScore-Qwen2-VL")
|
| 100 |
-
processor.push_to_hub("TIGER-Lab/VideoScore-Qwen2-VL")
|
| 101 |
-
exit(1)
|
| 102 |
-
|
| 103 |
# Messages containing a images list as a video and a text query
|
| 104 |
messages = [
|
| 105 |
{
|
|
|
|
| 95 |
# default processer
|
| 96 |
processor = Qwen2VLProcessor.from_pretrained(model_name)
|
| 97 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
# Messages containing a images list as a video and a text query
|
| 99 |
messages = [
|
| 100 |
{
|