Instructions to use relbert/relbert-roberta-base-nce-semeval2012-mask with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use relbert/relbert-roberta-base-nce-semeval2012-mask with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="relbert/relbert-roberta-base-nce-semeval2012-mask")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("relbert/relbert-roberta-base-nce-semeval2012-mask") model = AutoModel.from_pretrained("relbert/relbert-roberta-base-nce-semeval2012-mask", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download analogy.reverse.json from relbert/relbert-roberta-base-nce-semeval2012-mask: direct link, hf CLI and curl.
- Browser
- Download file 843 Bytes
-
https://huggingface.co/relbert/relbert-roberta-base-nce-semeval2012-mask/resolve/main/analogy.reverse.json
- Command line
-
hf download hf://relbert/relbert-roberta-base-nce-semeval2012-mask/analogy.reverse.json
-
curl -L -o analogy.reverse.json https://huggingface.co/relbert/relbert-roberta-base-nce-semeval2012-mask/resolve/main/analogy.reverse.json
843 Bytes
| {"scan/test": 0.2629950495049505, "sat_full/test": 0.5748663101604278, "sat/test": 0.5608308605341247, "u2/test": 0.543859649122807, "u4/test": 0.5601851851851852, "google/test": 0.904, "bats/test": 0.6725958866036688, "t_rex_relational_similarity/test": 0.6775956284153005, "conceptnet_relational_similarity/test": 0.38338926174496646, "nell_relational_similarity/test": 0.765, "scan/validation": 0.30337078651685395, "sat/validation": 0.7027027027027027, "u2/validation": 0.6666666666666666, "u4/validation": 0.6666666666666666, "google/validation": 0.92, "bats/validation": 0.7336683417085427, "semeval2012_relational_similarity/validation": 0.6962025316455697, "t_rex_relational_similarity/validation": 0.21774193548387097, "conceptnet_relational_similarity/validation": 0.2949640287769784, "nell_relational_similarity/validation": 0.5275} |