Instructions to use rooftopcoder/bart-base-coqa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rooftopcoder/bart-base-coqa with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("rooftopcoder/bart-base-coqa") model = AutoModelForSeq2SeqLM.from_pretrained("rooftopcoder/bart-base-coqa", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download predict_results.json from rooftopcoder/bart-base-coqa: direct link, hf CLI and curl.
- Browser
- Download file 270 Bytes
-
https://huggingface.co/rooftopcoder/bart-base-coqa/resolve/9eaff1e3acbdadcfcd5bf01cba5a5c492bc52cd1/predict_results.json
- Command line
-
hf download hf://rooftopcoder/bart-base-coqa@9eaff1e3acbdadcfcd5bf01cba5a5c492bc52cd1/predict_results.json
-
curl -L -o predict_results.json https://huggingface.co/rooftopcoder/bart-base-coqa/resolve/9eaff1e3acbdadcfcd5bf01cba5a5c492bc52cd1/predict_results.json
270 Bytes
| { | |
| "predict_accuracy": 0.08267568583239383, | |
| "predict_f1": 0.045617221543158844, | |
| "predict_loss": 0.8681505918502808, | |
| "predict_runtime": 259.1585, | |
| "predict_samples": 7983, | |
| "predict_samples_per_second": 30.804, | |
| "predict_steps_per_second": 1.925 | |
| } |