Modelpublic

KFC-F200/END_FM_DARE_0.7

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes12downloads

Model Card

dare_0.7

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

Merge Details

Merge Method

This model was merged using the Linear DARE merge method using unsloth/Llama-3.2-3B-Instruct as a base.

Models Merged

The following models were included in the merge:

—aabberick/Llama3.2-3b-H200-End_16bit
—aabberick/Llama3.2-3b-H200FamilyM

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: unsloth/Llama-3.2-3B-Instruct
    # No parameters necessary for base model
  - model: aabberick/Llama3.2-3b-H200-End_16bit
    parameters:
      density: 0.7
      weight: 0.5
  - model: aabberick/Llama3.2-3b-H200FamilyM
    parameters:
      density: 0.7
      weight: 0.5
merge_method: dare_linear
base_model: unsloth/Llama-3.2-3B-Instruct
parameters:
  int8_mask: false
dtype: bfloat16