Instructions to use google/tapas-medium-finetuned-wtq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/tapas-medium-finetuned-wtq with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("table-question-answering", model="google/tapas-medium-finetuned-wtq")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTableQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("google/tapas-medium-finetuned-wtq") model = AutoModelForTableQuestionAnswering.from_pretrained("google/tapas-medium-finetuned-wtq", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tf_model.h5 from google/tapas-medium-finetuned-wtq: direct link, hf CLI and curl.
- Browser
- Download file 168 MB
-
https://huggingface.co/google/tapas-medium-finetuned-wtq/resolve/main/tf_model.h5
- Command line
-
hf download hf://google/tapas-medium-finetuned-wtq/tf_model.h5
-
curl -L -o tf_model.h5 https://huggingface.co/google/tapas-medium-finetuned-wtq/resolve/main/tf_model.h5
168 MB
- Xet hash:
- 3c8d8f4da4690c3b8868b15bcbc713d50674e858ef09573cbab5f99d8c6a9fcf
- Size of remote file:
- 168 MB
- SHA256:
- 8668915a30bdca8a3faafd8d10e3c9791ac57593c1b53fa278582c6b77977a71
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.