Instructions to use prithivMLmods/Deepfake-Real-Class-Siglip2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use prithivMLmods/Deepfake-Real-Class-Siglip2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="prithivMLmods/Deepfake-Real-Class-Siglip2") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoProcessor, AutoModelForImageClassification processor = AutoProcessor.from_pretrained("prithivMLmods/Deepfake-Real-Class-Siglip2") model = AutoModelForImageClassification.from_pretrained("prithivMLmods/Deepfake-Real-Class-Siglip2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": 0.061126627027988434, | |
| "best_model_checkpoint": "Real-Fake-Class/checkpoint-3365", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 3365, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1485884101040119, | |
| "grad_norm": 3.8796277046203613, | |
| "learning_rate": 2.7979041916167666e-06, | |
| "loss": 0.2434, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2971768202080238, | |
| "grad_norm": 10.399986267089844, | |
| "learning_rate": 2.5733532934131734e-06, | |
| "loss": 0.1139, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4457652303120357, | |
| "grad_norm": 18.36138343811035, | |
| "learning_rate": 2.3488023952095807e-06, | |
| "loss": 0.0984, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.5943536404160475, | |
| "grad_norm": 8.896696090698242, | |
| "learning_rate": 2.124251497005988e-06, | |
| "loss": 0.0915, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7429420505200595, | |
| "grad_norm": 3.4077460765838623, | |
| "learning_rate": 1.8997005988023954e-06, | |
| "loss": 0.0839, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.8915304606240714, | |
| "grad_norm": 35.51144790649414, | |
| "learning_rate": 1.6751497005988027e-06, | |
| "loss": 0.0768, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9807306470489885, | |
| "eval_loss": 0.061126627027988434, | |
| "eval_model_preparation_time": 0.0062, | |
| "eval_runtime": 946.099, | |
| "eval_samples_per_second": 75.861, | |
| "eval_steps_per_second": 9.483, | |
| "step": 3365 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6730, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.016949169130807e+18, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |