Instructions to use morit/toxic_8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use morit/toxic_8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="morit/toxic_8")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("morit/toxic_8") model = AutoModelForSequenceClassification.from_pretrained("morit/toxic_8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download test/trainer_state.json from morit/toxic_8: direct link, hf CLI and curl.
- Browser
- Download file 578 Bytes
-
https://huggingface.co/morit/toxic_8/resolve/main/test/trainer_state.json
- Command line
-
hf download hf://morit/toxic_8/test/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/morit/toxic_8/resolve/main/test/trainer_state.json
578 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": 5591607072768.0, | |
| "train_loss": 0.8742923736572266, | |
| "train_runtime": 81.0645, | |
| "train_samples_per_second": 0.296, | |
| "train_steps_per_second": 0.037 | |
| } | |
| ], | |
| "max_steps": 3, | |
| "num_train_epochs": 3, | |
| "total_flos": 5591607072768.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |