Instructions to use alexionby/clip-roberta-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use alexionby/clip-roberta-finetuned with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="alexionby/clip-roberta-finetuned")# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("alexionby/clip-roberta-finetuned") model = AutoModel.from_pretrained("alexionby/clip-roberta-finetuned", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.0, | |
| "step": 30, | |
| "total_flos": 166896600000000.0, | |
| "train_loss": 2.739854176839193, | |
| "train_runtime": 34.0512, | |
| "train_samples_per_second": 36.709, | |
| "train_steps_per_second": 0.881 | |
| } | |
| ], | |
| "max_steps": 30, | |
| "num_train_epochs": 5, | |
| "total_flos": 166896600000000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |