Instructions to use davanstrien/clip-roberta-finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use davanstrien/clip-roberta-finetuned with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="davanstrien/clip-roberta-finetuned")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("davanstrien/clip-roberta-finetuned") model = AutoModel.from_pretrained("davanstrien/clip-roberta-finetuned", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download trainer_state.json from davanstrien/clip-roberta-finetuned: direct link, hf CLI and curl.
- Browser
- Download file 576 Bytes
-
https://huggingface.co/davanstrien/clip-roberta-finetuned/resolve/52d9d90bc731cefae7b7a1206337c2df2a4624f3/trainer_state.json
- Command line
-
hf download hf://davanstrien/clip-roberta-finetuned@52d9d90bc731cefae7b7a1206337c2df2a4624f3/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/davanstrien/clip-roberta-finetuned/resolve/52d9d90bc731cefae7b7a1206337c2df2a4624f3/trainer_state.json
576 Bytes
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.0, | |
| "step": 3, | |
| "total_flos": 4005518400000.0, | |
| "train_loss": 2.3376487096150718, | |
| "train_runtime": 3.066, | |
| "train_samples_per_second": 9.785, | |
| "train_steps_per_second": 0.978 | |
| } | |
| ], | |
| "max_steps": 3, | |
| "num_train_epochs": 3, | |
| "total_flos": 4005518400000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |