Instructions to use VenkatManda/BertMiniV3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use VenkatManda/BertMiniV3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="VenkatManda/BertMiniV3")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("VenkatManda/BertMiniV3") model = AutoModelForQuestionAnswering.from_pretrained("VenkatManda/BertMiniV3") - Notebooks
- Google Colab
- Kaggle
| { | |
| "eval_HasAns_exact": 22.97081167532987, | |
| "eval_HasAns_f1": 29.82730501295977, | |
| "eval_HasAns_total": 5002, | |
| "eval_NoAns_exact": 61.644657863145255, | |
| "eval_NoAns_f1": 61.644657863145255, | |
| "eval_NoAns_total": 4998, | |
| "eval_best_exact": 50.0, | |
| "eval_best_exact_thresh": 0.0, | |
| "eval_best_f1": 50.00666666666667, | |
| "eval_best_f1_thresh": 0.0, | |
| "eval_exact": 42.3, | |
| "eval_f1": 45.72961796748245, | |
| "eval_runtime": 188.1784, | |
| "eval_samples": 10000, | |
| "eval_samples_per_second": 53.141, | |
| "eval_steps_per_second": 6.643, | |
| "eval_total": 10000 | |
| } |