de-llama3-discoleo-instruct-8b-v0.1-x-meta-llama-3-8b-instruct-della_linear-50_50

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 meta-llama/Meta-Llama-3-8B-Instruct as a base.

Models Merged

The following models were included in the merge:

• DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1

Configuration

The following YAML configuration was used to produce this model:

merge_method: della_linear
models:
- model: DiscoResearch/Llama3-DiscoLeo-Instruct-8B-v0.1
  parameters:
    weight: 0.5
- model: meta-llama/Meta-Llama-3-8B-Instruct
  parameters:
    weight: 0.5
parameters:
  normalize: true
  int8_mask: true
  density: 0.5
  lambda: 1.0
  epsilon: 0.2
dtype: bfloat16
tokenizer:
  source: union
base_model: meta-llama/Meta-Llama-3-8B-Instruct
write_readme: README.md