Instructions to use tweettemposhift/hate-hate_temporal-bertweet-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tweettemposhift/hate-hate_temporal-bertweet-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="tweettemposhift/hate-hate_temporal-bertweet-large")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("tweettemposhift/hate-hate_temporal-bertweet-large") model = AutoModelForSequenceClassification.from_pretrained("tweettemposhift/hate-hate_temporal-bertweet-large") - Notebooks
- Google Colab
- Kaggle
| {"test/eval_loss": 0.6738409996032715, "test/eval_f1": 0.474820143884892, "test/eval_accuracy": 0.8515254237288136, "test/eval_runtime": 5.9786, "test/eval_samples_per_second": 246.712, "test/eval_steps_per_second": 30.944, "test_1/eval_loss": 0.7418155670166016, "test_1/eval_f1": 0.43636363636363634, "test_1/eval_accuracy": 0.8315217391304348, "test_1/eval_runtime": 1.4967, "test_1/eval_samples_per_second": 245.869, "test_1/eval_steps_per_second": 30.734, "test_2/eval_loss": 0.6136800050735474, "test_2/eval_f1": 0.41758241758241765, "test_2/eval_accuracy": 0.8559782608695652, "test_2/eval_runtime": 1.4928, "test_2/eval_samples_per_second": 246.519, "test_2/eval_steps_per_second": 30.815, "test_3/eval_loss": 0.5848008394241333, "test_3/eval_f1": 0.5825242718446602, "test_3/eval_accuracy": 0.8831521739130435, "test_3/eval_runtime": 1.4933, "test_3/eval_samples_per_second": 246.429, "test_3/eval_steps_per_second": 30.804, "test_4/eval_loss": 0.7544106245040894, "test_4/eval_f1": 0.46017699115044247, "test_4/eval_accuracy": 0.8355795148247979, "test_4/eval_runtime": 1.5069, "test_4/eval_samples_per_second": 246.205, "test_4/eval_steps_per_second": 31.19} |