Instructions to use haritzpuerto/MetaQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use haritzpuerto/MetaQA 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="haritzpuerto/MetaQA")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("haritzpuerto/MetaQA") model = AutoModel.from_pretrained("haritzpuerto/MetaQA", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Librarian Bot: Update Hugging Face dataset ID
Verified signatureThis pull request updates the ID of the dataset used to train the model to the new Hub identifier `google/boolq` (which has been migrated moved from `boolq`). We have been working to migrate datasets to their own repositories on the Hub, and this is part of that effort. Updating the dataset ID in the model card will ensure that the model card is correctly linked to the dataset repository on the Hub. This will also make it easier for people to find your model via the training data used to create it. This PR comes courtesy of [Librarian Bot](https://huggingface.co/librarian-bot). If you have any feedback, queries, or need assistance, please don't hesitate to reach out to [@davanstrien](https://huggingface.co/davanstrien).3baab0e
-
Create model.py
dd38fc4 -
Update inference.py
4b2efc2
-
Create README.md
0297073 -
Update inference.py
127b15f -
Create inference.py
9f26017 -
Update config.json
70a4de4 -
Upload tokenizer
7f5e0f3 -
Upload model
eda5cec -
initial commit
Haritz Puertobf48835