Instructions to use tweettemposhift/hate-hate_balance_temporal-bertweet-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tweettemposhift/hate-hate_balance_temporal-bertweet-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="tweettemposhift/hate-hate_balance_temporal-bertweet-base")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("tweettemposhift/hate-hate_balance_temporal-bertweet-base") model = AutoModelForSequenceClassification.from_pretrained("tweettemposhift/hate-hate_balance_temporal-bertweet-base") - Notebooks
- Google Colab
- Kaggle
| {"test/eval_loss": 0.6292451620101929, "test/eval_f1": 0.3613861386138614, "test/eval_accuracy": 0.8250847457627118, "test/eval_runtime": 2.2373, "test/eval_samples_per_second": 659.268, "test/eval_steps_per_second": 82.688, "test_1/eval_loss": 0.6818355917930603, "test_1/eval_f1": 0.3177570093457944, "test_1/eval_accuracy": 0.8016304347826086, "test_1/eval_runtime": 0.578, "test_1/eval_samples_per_second": 636.637, "test_1/eval_steps_per_second": 79.58, "test_2/eval_loss": 0.5244475603103638, "test_2/eval_f1": 0.38202247191011235, "test_2/eval_accuracy": 0.8505434782608695, "test_2/eval_runtime": 0.5692, "test_2/eval_samples_per_second": 646.515, "test_2/eval_steps_per_second": 80.814, "test_3/eval_loss": 0.5671004056930542, "test_3/eval_f1": 0.41666666666666663, "test_3/eval_accuracy": 0.8478260869565217, "test_3/eval_runtime": 0.5702, "test_3/eval_samples_per_second": 645.367, "test_3/eval_steps_per_second": 80.671, "test_4/eval_loss": 0.742672324180603, "test_4/eval_f1": 0.3392857142857143, "test_4/eval_accuracy": 0.8005390835579514, "test_4/eval_runtime": 0.5792, "test_4/eval_samples_per_second": 640.592, "test_4/eval_steps_per_second": 81.153} |