Old Metrics

  • loss: 1.1158
  • accuracy: 0.8265
  • precision: 0.8268
  • recall: 0.8265
  • precision_macro: 0.8014
  • recall_macro: 0.7830
  • macro_fpr: 0.0153
  • weighted_fpr: 0.0148
  • weighted_specificity: 0.9773
  • macro_specificity: 0.9869
  • weighted_sensitivity: 0.8265
  • macro_sensitivity: 0.7830
  • f1_micro: 0.8265
  • f1_macro: 0.7882
  • f1_weighted: 0.8252
  • runtime: 21.7379
  • samples_per_second: 59.3890
  • steps_per_second: 7.4520

InLegal-legal-merge-ties

InLegal-legal-merge-ties is a merge of the following models using mergekit:

🧩 Configuration

models:
  - model: xshubhamx/InLegalBERT
    parameters:
      density: 1
      weight: 1
  - model: xshubhamx/legal-bert-base-uncased
    parameters:
      density: 1
      weight: 1

merge_method: ties
base_model: xshubhamx/InLegalBERT
parameters:
  normalize: false
  int8_mask: true
dtype: float16
Downloads last month
107
Safetensors
Model size
109M params
Tensor type
FP16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.