Instructions to use am5uc/ServiceNow_Table_Question_Answering with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use am5uc/ServiceNow_Table_Question_Answering with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("table-question-answering", model="am5uc/ServiceNow_Table_Question_Answering")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTableQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("am5uc/ServiceNow_Table_Question_Answering") model = AutoModelForTableQuestionAnswering.from_pretrained("am5uc/ServiceNow_Table_Question_Answering", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -56,7 +56,7 @@ This model is designed for question answering over tabular data. It is mostly di
|
|
| 56 |
number of records in varying categories.
|
| 57 |
|
| 58 |
```python
|
| 59 |
-
saved_path = "
|
| 60 |
tokenizer = TapasTokenizer.from_pretrained(saved_path)
|
| 61 |
model = TapasForQuestionAnswering.from_pretrained(saved_path)
|
| 62 |
|
|
|
|
| 56 |
number of records in varying categories.
|
| 57 |
|
| 58 |
```python
|
| 59 |
+
saved_path = "am5uc/ServiceNow_Table_Question_Answering"
|
| 60 |
tokenizer = TapasTokenizer.from_pretrained(saved_path)
|
| 61 |
model = TapasForQuestionAnswering.from_pretrained(saved_path)
|
| 62 |
|