Instructions to use preneond/newlinefix-encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use preneond/newlinefix-encoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="preneond/newlinefix-encoder")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("preneond/newlinefix-encoder") model = AutoModelForTokenClassification.from_pretrained("preneond/newlinefix-encoder", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download predictor_config.json from preneond/newlinefix-encoder: direct link, hf CLI and curl.
- Browser
- Download file 659 Bytes
-
https://huggingface.co/preneond/newlinefix-encoder/resolve/main/predictor_config.json
- Command line
-
hf download hf://preneond/newlinefix-encoder/predictor_config.json
-
curl -L -o predictor_config.json https://huggingface.co/preneond/newlinefix-encoder/resolve/main/predictor_config.json
659 Bytes
| { | |
| "max_words": 180, | |
| "overlap": 64, | |
| "model_name": "distilroberta-base", | |
| "val_metrics": { | |
| "accuracy": 0.9795400902058844, | |
| "macro_f1_structural": 0.7832464081700393, | |
| "precision_JOIN": 0.887536112257532, | |
| "recall_JOIN": 0.9830857142857143, | |
| "f1_JOIN": 0.9328706214076565, | |
| "precision_SPACE": 0.9972153093227003, | |
| "recall_SPACE": 0.9830608435529667, | |
| "f1_SPACE": 0.9900874903362599, | |
| "precision_NEWLINE": 0.6938279112192156, | |
| "recall_NEWLINE": 0.8199784405318002, | |
| "f1_NEWLINE": 0.7516469038208169, | |
| "precision_PARA": 0.5414314516129032, | |
| "recall_PARA": 0.8623956326268465, | |
| "f1_PARA": 0.6652216992816448 | |
| } | |
| } | |