Instructions to use DayCardoso/roberta-base-multi-head with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DayCardoso/roberta-base-multi-head with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, RobertaForMultiLabelMultiHead tokenizer = AutoTokenizer.from_pretrained("DayCardoso/roberta-base-multi-head") model = RobertaForMultiLabelMultiHead.from_pretrained("DayCardoso/roberta-base-multi-head", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from DayCardoso/roberta-base-multi-head: direct link, hf CLI and curl.
- Browser
- Download file 458 Bytes
-
https://huggingface.co/DayCardoso/roberta-base-multi-head/resolve/main/eval_results.json
- Command line
-
hf download hf://DayCardoso/roberta-base-multi-head/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/DayCardoso/roberta-base-multi-head/resolve/main/eval_results.json
458 Bytes
| { | |
| "epoch": 3.259558164180321, | |
| "eval_accuracy": 0.5679713544882085, | |
| "eval_f1_macro": 0.535328565889324, | |
| "eval_f1_micro": 0.5679713544882085, | |
| "eval_loss": 0.45331016182899475, | |
| "eval_precision_macro": 0.5489792373431622, | |
| "eval_recall_macro": 0.5315336191512473, | |
| "eval_roc_auc": 0.786883264678242, | |
| "eval_runtime": 53.0285, | |
| "eval_samples": 8099, | |
| "eval_samples_per_second": 152.729, | |
| "eval_steps_per_second": 76.374 | |
| } |