Instructions to use consciousAI/question-answering-roberta-base-s with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use consciousAI/question-answering-roberta-base-s 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="consciousAI/question-answering-roberta-base-s")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("consciousAI/question-answering-roberta-base-s") model = AutoModelForQuestionAnswering.from_pretrained("consciousAI/question-answering-roberta-base-s", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Anshoo Mehra commited on
Commit 路
2b09f42
1
Parent(s): c208ba9
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,9 +13,9 @@ model-index:
|
|
| 13 |
The model is intended to be used for Q&A task, given the question & context, the model would attempt to infer the answer text, answer span & confidence score.<br>
|
| 14 |
Model is encoder-only (roberta-base) with QuestionAnswering LM Head, fine-tuned on SQUADx dataset with **exact_match:** 86.14 & **f1:** 92.330 performance scores.
|
| 15 |
|
| 16 |
-
|
| 17 |
|
| 18 |
-
|
| 19 |
|
| 20 |
Example code:
|
| 21 |
```
|
|
|
|
| 13 |
The model is intended to be used for Q&A task, given the question & context, the model would attempt to infer the answer text, answer span & confidence score.<br>
|
| 14 |
Model is encoder-only (roberta-base) with QuestionAnswering LM Head, fine-tuned on SQUADx dataset with **exact_match:** 86.14 & **f1:** 92.330 performance scores.
|
| 15 |
|
| 16 |
+
[Live Demo: Question Answering Leveraging Encoders vs Generative](https://huggingface.co/spaces/anshoomehra/question_answering)
|
| 17 |
|
| 18 |
+
Please follow this link for [Generative Question Answering](https://huggingface.co/anshoomehra/question-answering-generative-t5-v1-base-s-q-c/)
|
| 19 |
|
| 20 |
Example code:
|
| 21 |
```
|