Text Classification
Transformers
Safetensors
Vietnamese
xlm-roberta
vietnamese
fact-checking
claim-verification
natural-language-inference
vifactcheck
full-context
eacl-2027
Instructions to use BaoNhan/bn-newsbert-ViFactCheck-FC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BaoNhan/bn-newsbert-ViFactCheck-FC with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="BaoNhan/bn-newsbert-ViFactCheck-FC")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("BaoNhan/bn-newsbert-ViFactCheck-FC") model = AutoModelForSequenceClassification.from_pretrained("BaoNhan/bn-newsbert-ViFactCheck-FC", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "test_macro_f1_mean": 0.6822236082683636, | |
| "test_macro_f1_std": 0.020221173156763098, | |
| "test_macro_f1_text": "0.6822 ± 0.0202", | |
| "test_accuracy_mean": 0.682780847145488, | |
| "test_accuracy_std": 0.019840203891726714, | |
| "test_accuracy_text": "0.6828 ± 0.0198", | |
| "test_macro_precision_mean": 0.6844905259101943, | |
| "test_macro_precision_std": 0.020775638611263955, | |
| "test_macro_precision_text": "0.6845 ± 0.0208", | |
| "test_macro_recall_mean": 0.6814768739986444, | |
| "test_macro_recall_std": 0.020071255760093012, | |
| "test_macro_recall_text": "0.6815 ± 0.0201", | |
| "dev_macro_f1_mean": 0.7188106084932735, | |
| "dev_macro_f1_std": 0.0063273577854815344, | |
| "dev_macro_f1_text": "0.7188 ± 0.0063", | |
| "task": "ViFactCheck-full-context", | |
| "dataset": "ViFactCheck", | |
| "model_key": "bn_newsbert", | |
| "model_name": "BN-NewsBERT", | |
| "base_model": "BaoNhan/BN-NewsBERT", | |
| "seeds": [ | |
| 22, | |
| 42, | |
| 202 | |
| ], | |
| "representative_seed": 202, | |
| "selection_rule": "maximum development Macro-F1; seed ascending tie-break", | |
| "split_policy": "merged_stratified_80_10_10", | |
| "split_seed": 42, | |
| "max_length": 256, | |
| "epochs": 3, | |
| "effective_batch_size": 8 | |
| } |