Feature Extraction
Transformers
Safetensors
score_predictor
deberta-v3
regression
text-evaluation
multilingual
trust-remote-code
custom_code
Instructions to use QCRI/OmniScore-deberta-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use QCRI/OmniScore-deberta-v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="QCRI/OmniScore-deberta-v3", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("QCRI/OmniScore-deberta-v3", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "mse_overall": 1.4024023678171664, | |
| "mse_informativeness": 2.461441272473649, | |
| "mse_clarity": 1.2284622644467016, | |
| "mse_plausibility": 1.0879825710281692, | |
| "mse_faithfulness": 0.8317233633201462, | |
| "rmse_overall": 1.158077748242096, | |
| "rmse_informativeness": 1.5688981077411144, | |
| "rmse_clarity": 1.1083601690996936, | |
| "rmse_plausibility": 1.0430640301669736, | |
| "rmse_faithfulness": 0.9119886859606023, | |
| "mae_overall": 0.899240226476647, | |
| "mae_informativeness": 1.2259089428195094, | |
| "mae_clarity": 0.8495489541516034, | |
| "mae_plausibility": 0.7888888825356873, | |
| "mae_faithfulness": 0.7326141263997884, | |
| "pearson_informativeness": 0.011997820511715235, | |
| "pearson_pval_informativeness": 0.11588154802545263, | |
| "pearson_clarity": 0.12849459314220896, | |
| "pearson_pval_clarity": 3.890738005032354e-64, | |
| "pearson_plausibility": 0.11834201691919606, | |
| "pearson_pval_plausibility": 1.304550908503357e-54, | |
| "pearson_faithfulness": 0.18031506133750783, | |
| "pearson_pval_faithfulness": 1.8522469152476205e-125, | |
| "pearson_overall": 0.10978737297765703, | |
| "spearman_informativeness": 0.014049690666530525, | |
| "spearman_pval_informativeness": 0.06558977589044894, | |
| "spearman_clarity": 0.07886223322374226, | |
| "spearman_pval_clarity": 4.161494147791507e-25, | |
| "spearman_plausibility": 0.028879234142028146, | |
| "spearman_pval_plausibility": 0.0001535624767660131, | |
| "spearman_faithfulness": 0.13269205496372913, | |
| "spearman_pval_faithfulness": 2.6118969073270385e-68, | |
| "spearman_overall": 0.06362080324900751, | |
| "r2_informativeness": -2.7357081705124537, | |
| "r2_clarity": -0.6323411816544322, | |
| "r2_plausibility": -0.7522394899465792, | |
| "r2_faithfulness": -0.4469073644134465, | |
| "r2_overall": -1.141799051631728, | |
| "accuracy_0.5_overall": 0.3543085880640466, | |
| "accuracy_0.5_informativeness": 0.3000873362445415, | |
| "accuracy_0.5_clarity": 0.35656477438136824, | |
| "accuracy_0.5_plausibility": 0.3750218340611354, | |
| "accuracy_0.5_faithfulness": 0.3855604075691412, | |
| "accuracy_1.0_overall": 0.7163755458515284, | |
| "accuracy_1.0_informativeness": 0.4880349344978166, | |
| "accuracy_1.0_clarity": 0.7710625909752548, | |
| "accuracy_1.0_plausibility": 0.8298107714701601, | |
| "accuracy_1.0_faithfulness": 0.7765938864628821, | |
| "exact_match_overall": 0.3543085880640466, | |
| "exact_match_informativeness": 0.3000873362445415, | |
| "exact_match_clarity": 0.35656477438136824, | |
| "exact_match_plausibility": 0.3750218340611354, | |
| "exact_match_faithfulness": 0.3855604075691412, | |
| "exact_match_all_scores": 0.029286754002911208, | |
| "max_error_overall": 3.9264787435531616, | |
| "max_error_informativeness": 3.946486473083496, | |
| "max_error_clarity": 3.9604382514953613, | |
| "max_error_plausibility": 3.9576148986816406, | |
| "max_error_faithfulness": 3.8413753509521484, | |
| "bias_overall": 0.11064034007522217, | |
| "bias_informativeness": -0.8433933716916968, | |
| "bias_clarity": 0.6641923878737759, | |
| "bias_plausibility": 0.6784779361935855, | |
| "bias_faithfulness": -0.05671559207477597, | |
| "pred_mean": 4.212707297862704, | |
| "pred_std": 0.9062484396734384, | |
| "pred_min": 1.2022016048431396, | |
| "pred_max": 4.963072776794434, | |
| "label_mean": 4.102066957787482, | |
| "label_std": 0.8079869363161494, | |
| "label_min": 1.0, | |
| "label_max": 5.0, | |
| "num_samples": 17175 | |
| } |