Instructions to use Terrificfantasm/bert-base-uncased-squad-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Terrificfantasm/bert-base-uncased-squad-qa with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="Terrificfantasm/bert-base-uncased-squad-qa")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Terrificfantasm/bert-base-uncased-squad-qa") model = AutoModelForQuestionAnswering.from_pretrained("Terrificfantasm/bert-base-uncased-squad-qa", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download evaluation.json from Terrificfantasm/bert-base-uncased-squad-qa: direct link, hf CLI and curl.
- Browser
- Download file 1.04 kB
-
https://huggingface.co/Terrificfantasm/bert-base-uncased-squad-qa/resolve/main/evaluation.json
- Command line
-
hf download hf://Terrificfantasm/bert-base-uncased-squad-qa/evaluation.json
-
curl -L -o evaluation.json https://huggingface.co/Terrificfantasm/bert-base-uncased-squad-qa/resolve/main/evaluation.json
1.04 kB
| { | |
| "selected_method": "full_finetuning", | |
| "comparison": [ | |
| { | |
| "method": "partial_finetuning", | |
| "best_epoch": 3, | |
| "best_val_f1": 58.37301797522163, | |
| "trainable_parameters": 14177282, | |
| "total_parameters": 108893186, | |
| "frozen_parameters_verified": true, | |
| "train_seconds": 305.73657120007556, | |
| "peak_allocated_gpu_bytes": 838847488, | |
| "test_exact_match": 47.8, | |
| "test_f1": 61.74906537716013, | |
| "test_loss": 1.9262970177410859, | |
| "selected": false | |
| }, | |
| { | |
| "method": "full_finetuning", | |
| "best_epoch": 3, | |
| "best_val_f1": 77.28249836283702, | |
| "trainable_parameters": 108893186, | |
| "total_parameters": 108893186, | |
| "frozen_parameters_verified": false, | |
| "train_seconds": 845.9825941000599, | |
| "peak_allocated_gpu_bytes": 2699117056, | |
| "test_exact_match": 73.6, | |
| "test_f1": 83.27740228969499, | |
| "test_loss": 1.2625670313247905, | |
| "selected": true | |
| } | |
| ], | |
| "test_used_for_selection": false | |
| } | |