Question Answering
Transformers
PyTorch
TensorBoard
Habana
roberta
Generated from Trainer
Eval Results (legacy)
Instructions to use nbroad/rob-base-superqa1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nbroad/rob-base-superqa1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="nbroad/rob-base-superqa1")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("nbroad/rob-base-superqa1") model = AutoModelForQuestionAnswering.from_pretrained("nbroad/rob-base-superqa1") - Notebooks
- Google Colab
- Kaggle
| { | |
| "hmp_bf16_ops": [ | |
| "add", | |
| "addmm", | |
| "bmm", | |
| "conv1d", | |
| "div", | |
| "dropout", | |
| "gelu", | |
| "iadd", | |
| "linear", | |
| "layer_norm", | |
| "matmul", | |
| "mm", | |
| "rsub", | |
| "softmax", | |
| "truediv" | |
| ], | |
| "hmp_fp32_ops": [ | |
| "embedding", | |
| "nll_loss", | |
| "log_softmax" | |
| ], | |
| "hmp_is_verbose": false, | |
| "hmp_opt_level": "O1", | |
| "optimum_version": "1.3.0", | |
| "transformers_version": "4.21.1", | |
| "use_fused_adam": true, | |
| "use_fused_clip_norm": true, | |
| "use_habana_mixed_precision": true | |
| } | |