007ankit/della-linear-BioMistral-mistral-hindi

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Linear DELLA merge method using BioMistral/BioMistral-7B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: BioMistral/BioMistral-7B
    parameters:
      density: 1        # Fraction of weights in differences from the base model to retain
      epsilon: 0.1      # Maximum change in drop probability based on magnitude (range: density ± epsilon)
      weight: 1
      lambda: 0.9

merge_method: della_linear
base_model: BioMistral/BioMistral-7B

parameters:
  density: 1            # Fraction of weights in differences from the base model to retain
  epsilon: 0.1          # Maximum change in drop probability (range: density ± epsilon, ensure 0 <= value <= 1)
  weight: 1
  lambda: 0.9
  normalize: true
  int8_mask: true

dtype: bfloat16
name: OdiaGenAI/mistral_hindi_7b_base_v1