Alignment-Lab-AI/Scrollplay

output

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

Merge Details

Merge Method

This model was merged using the breadcrumbs_ties merge method using tavtav/eros-7b-test as a base.

Models Merged

The following models were included in the merge:

• Nexusflow/Starling-LM-7B-beta

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - model: tavtav/eros-7b-test
    layer_range: [0, 32]
  - model: Nexusflow/Starling-LM-7B-beta
    layer_range: [0, 32]
    parameters:
      weight: [1, 0.686, 0.37185, 0.686, 1]
      density: [0.9, 0.7, 0.9] # density gradient
      gamma: [0.01, 0.03, 0.02, 0.01] # weight gradient
tokenizer_source: base
merge_method: breadcrumbs_ties
base_model: tavtav/eros-7b-test
parameters:
  normalize: true
dtype: bfloat16
name: scringle