llama3-1b-breadcrumbs-ties-v2
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Model Breadcrumbs with TIES merge method using meta-llama/Llama-3.2-1B as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
base_model: meta-llama/Llama-3.2-1B
dtype: float16
merge_method: breadcrumbs_ties
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 16]
        model: Alelcv27/llama3-1b-math-dpo
        parameters:
          density: 0.5
          gamma: 0.01
          weight: 0.8
      - layer_range: [0, 16]
        model: Alelcv27/llama3-1b-code-dpo
        parameters:
          density: 0.6
          gamma: 0.02
          weight: 0.8
      - layer_range: [0, 16]
        model: meta-llama/Llama-3.2-1B
parameters:
  lambda: 0.8
  normalize: 1.0
- Downloads last month
- 18
Model tree for Alelcv27/llama3-1b-breadcrumbs-ties-v2
Merge model
	
	
this model