Instructions to use keras-io/transformers-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use keras-io/transformers-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="keras-io/transformers-qa")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("keras-io/transformers-qa") model = AutoModelForQuestionAnswering.from_pretrained("keras-io/transformers-qa", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
6e5a80b
1
Parent(s): 4cb67ab
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,11 +12,10 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 12 |
|
| 13 |
# transformers-qa
|
| 14 |
|
| 15 |
-
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
- Train Loss: 0.9300
|
| 18 |
- Validation Loss: 1.1437
|
| 19 |
-
- Epoch: 1
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 12 |
|
| 13 |
# transformers-qa
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the SQuAD dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
- Train Loss: 0.9300
|
| 18 |
- Validation Loss: 1.1437
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|