Instructions to use franklu/pubmed_bert_squadv2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use franklu/pubmed_bert_squadv2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="franklu/pubmed_bert_squadv2")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("franklu/pubmed_bert_squadv2") model = AutoModelForQuestionAnswering.from_pretrained("franklu/pubmed_bert_squadv2") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 2.0, | |
| "eval_HasAns_exact": 73.26248313090419, | |
| "eval_HasAns_f1": 79.53074066003731, | |
| "eval_HasAns_total": 5928, | |
| "eval_NoAns_exact": 81.53069806560134, | |
| "eval_NoAns_f1": 81.53069806560134, | |
| "eval_NoAns_total": 5945, | |
| "eval_best_exact": 77.4025098964036, | |
| "eval_best_exact_thresh": 0.0, | |
| "eval_best_f1": 80.53215115242146, | |
| "eval_best_f1_thresh": 0.0, | |
| "eval_exact": 77.4025098964036, | |
| "eval_f1": 80.53215115242146, | |
| "eval_samples": 12271, | |
| "eval_total": 11873 | |
| } |