Modelpublic

TareksGraveyard/Experimental-Base-V1

sourceHugging Facellama3.3updated 2y agoView on Hugging Face

1likes22downloads

Model Card

EXPERIMENT. WIP

merge

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

Merge Details

Merge Method

This model was merged using the Task Arithmetic merge method using ./Llama-3.3-70B-Instruct + ./Test_Lora as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

yaml

base_model: ./Llama-3.3-70B-Instruct+./Test_Lora
dtype: float32
merge_method: task_arithmetic
parameters:
  normalize: false
slices:
- sources:
  - layer_range: [0, 80]
    model: ./Llama-3.3-70B-Instruct+./Test_Lora
    parameters:
      weight: 1.0