Instructions to use henryscheible/stereoset_binary_bert_predheadonly with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use henryscheible/stereoset_binary_bert_predheadonly with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="henryscheible/stereoset_binary_bert_predheadonly")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("henryscheible/stereoset_binary_bert_predheadonly") model = AutoModelForSequenceClassification.from_pretrained("henryscheible/stereoset_binary_bert_predheadonly", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download validation.json from henryscheible/stereoset_binary_bert_predheadonly: direct link, hf CLI and curl.
- Browser
- Download file 794 Bytes
-
https://huggingface.co/henryscheible/stereoset_binary_bert_predheadonly/resolve/main/validation.json
- Command line
-
hf download hf://henryscheible/stereoset_binary_bert_predheadonly/validation.json
-
curl -L -o validation.json https://huggingface.co/henryscheible/stereoset_binary_bert_predheadonly/resolve/main/validation.json
794 Bytes
| {"best_model_step": "2.10", "best_model_acc": 0.5517647058823529, "eval_results": {"0.0": {"accuracy": 0.44588235294117645}, "0.10": {"accuracy": 0.52}, "0.20": {"accuracy": 0.5423529411764706}, "0.30": {"accuracy": 0.548235294117647}, "0.40": {"accuracy": 0.5517647058823529}, "0.50": {"accuracy": 0.5376470588235294}, "1.0": {"accuracy": 0.5364705882352941}, "1.10": {"accuracy": 0.5517647058823529}, "1.20": {"accuracy": 0.5423529411764706}, "1.30": {"accuracy": 0.5364705882352941}, "1.40": {"accuracy": 0.5435294117647059}, "1.50": {"accuracy": 0.5494117647058824}, "2.0": {"accuracy": 0.5505882352941176}, "2.10": {"accuracy": 0.5517647058823529}, "2.20": {"accuracy": 0.5423529411764706}, "2.30": {"accuracy": 0.54}, "2.40": {"accuracy": 0.5388235294117647}, "2.50": {"accuracy": 0.54}}} |