Edit model card

Metrics

  • loss: 3.3568
  • accuracy: 0.1681
  • precision: 0.1690
  • recall: 0.1681
  • precision_macro: 0.0609
  • recall_macro: 0.0684
  • macro_fpr: 0.1313
  • weighted_fpr: 0.2612
  • weighted_specificity: 0.8641
  • macro_specificity: 0.9355
  • weighted_sensitivity: 0.1681
  • macro_sensitivity: 0.0684
  • f1_micro: 0.1681
  • f1_macro: 0.0473
  • f1_weighted: 0.1340
  • runtime: 51.7340
  • samples_per_second: 24.9550
  • steps_per_second: 3.1310

legal-InLegal-merge-passthrough

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

🧩 Configuration

slices:
  - sources:
      - model: xshubhamx/legal-bert-base-uncased
        layer_range: [0, 11]
  - sources:
      - model: xshubhamx/InLegalBERT
        layer_range: [0, 11]
merge_method: passthrough
dtype: bfloat16
Downloads last month
8
Safetensors
Model size
180M params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.