Instructions to use Hieu/scam-detection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Hieu/scam-detection with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Hieu/scam-detection")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Hieu/scam-detection") model = AutoModelForSequenceClassification.from_pretrained("Hieu/scam-detection", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download trainer_state.json from Hieu/scam-detection: direct link, hf CLI and curl.
- Browser
- Download file 480 Bytes
-
https://huggingface.co/Hieu/scam-detection/resolve/main/trainer_state.json
- Command line
-
hf download hf://Hieu/scam-detection/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/Hieu/scam-detection/resolve/main/trainer_state.json
480 Bytes
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.803921568627452, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.8, | |
| "learning_rate": 9.80392156862745e-07, | |
| "loss": 0.0184, | |
| "step": 500 | |
| } | |
| ], | |
| "max_steps": 510, | |
| "num_train_epochs": 10, | |
| "total_flos": 2069368450406400.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |