Instructions to use ruyadisk/span_selection with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ruyadisk/span_selection 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="ruyadisk/span_selection")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("ruyadisk/span_selection") model = AutoModelForQuestionAnswering.from_pretrained("ruyadisk/span_selection", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_nbest_predictions.json from ruyadisk/span_selection: direct link, hf CLI and curl.
- Browser
- Download file 12.7 MB
-
https://huggingface.co/ruyadisk/span_selection/resolve/main/eval_nbest_predictions.json
- Command line
-
hf download hf://ruyadisk/span_selection/eval_nbest_predictions.json
-
curl -L -o eval_nbest_predictions.json https://huggingface.co/ruyadisk/span_selection/resolve/main/eval_nbest_predictions.json
12.7 MB
- Xet hash:
- eba39fdf5949e83be3cd41aa1f835d6e147044ceda5d5146c5d1a974b81f841d
- Size of remote file:
- 12.7 MB
- SHA256:
- 6a9d39b2ae61810d4af10050929111b828f54623da44db0c799547b080495f55
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.