Instructions to use DS4AI-UPB/distilbert-videomae-misinfo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DS4AI-UPB/distilbert-videomae-misinfo with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("DS4AI-UPB/distilbert-videomae-misinfo", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "text_model_name": "distilbert-base-uncased", | |
| "video_model_name": "MCG-NJU/videomae-base-finetuned-kinetics", | |
| "num_labels": 2, | |
| "text_max_length": 256, | |
| "batch_size": 2, | |
| "dropout": 0.1, | |
| "early_stopping_patience": 3, | |
| "fusion_hidden_dim": 256, | |
| "gradient_accumulation_steps": 1, | |
| "learning_rate": 2e-05, | |
| "lr_scheduler_type": "linear", | |
| "max_grad_norm": 1.0, | |
| "num_train_epochs": 30, | |
| "text_lora_alpha": 16, | |
| "text_lora_dropout": 0.05, | |
| "text_lora_r": 8, | |
| "text_proj_dim": 256, | |
| "video_lora_alpha": 32, | |
| "video_lora_dropout": 0.05, | |
| "video_lora_r": 16, | |
| "video_proj_dim": 256, | |
| "warmup_ratio": 0.0, | |
| "weight_decay": 0.01 | |
| } |