Video-Text-to-Text
Transformers
Safetensors
English
soccer_qa_4b
soccer
video-qa
question-answering
vision-language
multimodal
sports-analysis
Instructions to use sportsvision/soccer-qa-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sportsvision/soccer-qa-4b with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("sportsvision/soccer-qa-4b", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload requirements.txt
Browse files- requirements.txt +25 -0
requirements.txt
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
torch>=2
|
| 2 |
+
torchvision
|
| 3 |
+
tensorboard
|
| 4 |
+
wandb
|
| 5 |
+
iopath
|
| 6 |
+
pyyaml
|
| 7 |
+
numpy
|
| 8 |
+
opencv-python
|
| 9 |
+
submitit
|
| 10 |
+
braceexpand
|
| 11 |
+
webdataset
|
| 12 |
+
timm
|
| 13 |
+
transformers
|
| 14 |
+
peft
|
| 15 |
+
decord
|
| 16 |
+
pandas
|
| 17 |
+
einops
|
| 18 |
+
beartype
|
| 19 |
+
psutil
|
| 20 |
+
h5py
|
| 21 |
+
fire
|
| 22 |
+
python-box
|
| 23 |
+
scikit-image
|
| 24 |
+
ftfy
|
| 25 |
+
jupyter
|