Instructions to use BSC-LT/NextProcurement_pdfutils with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BSC-LT/NextProcurement_pdfutils with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="BSC-LT/NextProcurement_pdfutils")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("BSC-LT/NextProcurement_pdfutils") model = AutoModelForSequenceClassification.from_pretrained("BSC-LT/NextProcurement_pdfutils", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download eval_results.json from BSC-LT/NextProcurement_pdfutils: direct link, hf CLI and curl.
- Browser
- Download file 311 Bytes
-
https://huggingface.co/BSC-LT/NextProcurement_pdfutils/resolve/main/eval_results.json
- Command line
-
hf download hf://BSC-LT/NextProcurement_pdfutils/eval_results.json
-
curl -L -o eval_results.json https://huggingface.co/BSC-LT/NextProcurement_pdfutils/resolve/main/eval_results.json
311 Bytes
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.9514443761524278, | |
| "eval_combined_score": 0.955208035907946, | |
| "eval_f1": 0.9589716956634641, | |
| "eval_loss": 0.19619590044021606, | |
| "eval_runtime": 32.3829, | |
| "eval_samples": 6508, | |
| "eval_samples_per_second": 200.97, | |
| "eval_steps_per_second": 12.568 | |
| } |